EP1579386A1 - Procede et dispositif de detection de points d'interet dans une image numerique source, programme d'ordinateur et support de donees correspondants - Google Patents
Procede et dispositif de detection de points d'interet dans une image numerique source, programme d'ordinateur et support de donees correspondantsInfo
- Publication number
- EP1579386A1 EP1579386A1 EP03725291A EP03725291A EP1579386A1 EP 1579386 A1 EP1579386 A1 EP 1579386A1 EP 03725291 A EP03725291 A EP 03725291A EP 03725291 A EP03725291 A EP 03725291A EP 1579386 A1 EP1579386 A1 EP 1579386A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- image
- wavelet
- interest
- resolution
- detail
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/168—Segmentation; Edge detection involving transform domain methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/52—Scale-space analysis, e.g. wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
Definitions
- the field of the invention is that of the detection of points of interest, also called salient points in a digital image. More specifically, the invention relates to a technique for detecting points of interest implementing a wavelet type approach.
- a point of interest can be considered as the representative of a spatial region of the image conveying an important part of the information.
- the detection of salient points corresponding to the corners of objects is of little interest. Indeed, the corners are generally isolated points, representing only a small part of the information contained in the image. In addition, their detection generates clusters of salient points in the case of textured or noisy regions.
- M X ⁇ y is a matrix defined by:
- M x G ( ⁇ ) ® ( ⁇ .y) ⁇ x ( ⁇ .y) iy ( ⁇ > y)
- * t * ® denotes the convolution product; *> I x (resp. I y ) denotes the first derivative of / in the direction x (resp. Y);
- *> J is a generally used constant with a value of 0.04.
- the salient points are then defined by the positive local extrema of the quantity R xy .
- the image / is of size 2 N x2 N.
- N mveaux where the level 0 corresponds to the original image and the level Nl corresponds to an image of 1 pixel.
- the contrast at point P is defined by:
- G k (P) defines the local luminance at point P and at level k
- B k (P) defines the luminance of the local background at point P and at level k
- a salient point is a point characterized by a high value of the local contrast.
- the authors introduce a new quantity in order to obtain a zero value for a situation of non-contrast and a value greater than zero everywhere else.
- This new quantity is defined by:
- the salient points are defined by the local maxima of C k * greater than a fixed threshold.
- the detector of salient points initially presented in [11] is undoubtedly the closest to the present invention since it is also based on the use of the wavelet theory. Indeed, the authors consider that the points carrying a significant part of the information are located in the regions of the image having high frequencies. By using wavelets with compact support, the authors are able to determine a set of points of the signal / (which one supposes for the moment mono-dimensional) which were used to calculate any coefficient wavelet D 2] f (n), and this, at any resolution 2 J (j ⁇ -1).
- p denotes the regularity of the wavelet base used (i.e. the size of the wavelet filter) and N denotes the length of the original signal
- each wavelet coefficient D 2j f (n) is calculated from 2 ⁇ J p points of the signal / Its son coefficients C (D 2J f (n)) give the variation of a subset of these 2 ⁇ ! points.
- the most salient subset is the one with the maximum wavelet coefficient (in absolute value) at resolution level 2 y + 1 .
- the authors apply the same approach to each of the three sub-bands D 2j I, D 2 jI, D 2 jI where I denotes the original image.
- the spatial support of the wavelet base is 2px2p.
- the method searches, among the child coefficients of a given coefficient, for the one whose amplitude is maximum. If different coefficients of different orientations lead to the same pixel of /, then this pixel is considered as a salient point.
- the invention therefore aims in particular to overcome the various drawbacks of the state of the art.
- an objective of the invention is to provide a technique for detecting salient points corresponding to a high frequency, and not favoring any particular direction in the image.
- Another object of the invention is to provide such a technique, which requires a reduced number of operations, compared to known techniques.
- an objective of the invention is to provide such a technique making it possible to use wavelet bases with a large support.
- this method comprises the following steps:
- the source image is called an original image or an image having undergone a preprocessing (gradient calculation, change in color space, etc.).
- At least two detail images corresponding to at least two directions predetermined by said wavelet transformation are determined for each level of decomposition.
- This transformation into wavelets can in particular use first or second generation wavelets (mesh-based).
- said detail images may include:
- the method of the invention comprises a step of merging the coefficients of said detail images, so as not to favor any direction of said source image.
- said step of constructing a tree structure is based on a Zerotree type approach.
- each point of the minimum resolution scale image is the root of a tree to which a son node is associated with each of the wavelet coefficients of each of said image or images of details located at the same location, then we recursively associate , at each child node of given level of resolution, four child nodes formed by the wavelet coefficients of the image of details of the same type and of the previous level of resolution, and associated with the corresponding region of the source image.
- said selection step implements a step of constructing at least one saliency map, assigning to said wavelet coefficients a saliency value representative of its interest.
- a saliency map is constructed for each of said resolution levels.
- the information associated with the three wavelet coefficients corresponding to the three detail images is merged for each saliency value, so as not to favor any direction in the image.
- a saliency value of a given wavelet coefficient of a given resolution level takes into account the salience value (s) of the wavelet coefficients descending in said tree structure of said given wavelet coefficient.
- a salience value is a linear relation of the associated wavelet coefficients.
- the salience value of a given wavelet coefficient is calculated from the following equations:
- the parameter ⁇ k can for example be equal to -1 / r for all the values of k.
- said selection step comprises a step of constructing a tree structure of said salience values, advantageously based on a Zerotree type approach.
- said selection step advantageously comprises the steps of:
- said step of selecting the branch having the highest saliency value implements a course of the corresponding tree from its root, and a selection at each level of the tree of the child node with the highest salience value.
- the invention allows numerous wavelet transformations to be used.
- the Haar base is implemented.
- the minimum resolution level is 2 " ⁇
- the method of the invention can also comprise a step of calculating an image signature, from a predetermined number of points of interest of said image.
- Said signature can thus in particular be used for the indexing of images by their content.
- the invention finds applications in numerous fields, and for example for:
- the invention also relates to the devices for detecting points of interest in a source digital image implementing the method as described above.
- the invention also relates to computer programs comprising program code instructions for executing the steps of the method of detection of points of interest described above, and digital data carriers usable by a computer carrying such a program.
- FIG. 1 illustrates the principle multi-resolution analysis of an image I by transformation into wavelets
- Figure 2 shows schematically a wavelet transformation
- FIG. 3 is a representation of a tree of wavelet coefficients according to the invention
- FIG. 4 shows an example of saliency maps, and the corresponding salience trees
- - Figure 5 illustrates the salience of a branch of the tree of Figure
- An object of the invention is therefore the detection of the salient points of an image I. These points correspond to the pixels of / belonging to regions of high frequency. To do this, we base our on the wavelet theory [1] [2] [3]. Annex A provides a brief presentation of this theory.
- the wavelet transform is a multi-resolution representation of the image which allows the image to be expressed at different resolutions -, -, etc.
- the invention consists in first choosing a wavelet base and a minimum resolution level 2 r (r ⁇ -1). Once the wavelet transformation has been carried out, we propose to browse each of the three detail images D l I,
- a coefficient having a significant salience corresponds to a region of / having high frequencies.
- a significant wavelet modulus coefficient at resolution 2 r (r ⁇ -1) corresponds to an outline of the image A +1 1 in a particular direction (horizontal, vertical or oblique).
- the Zerotree approach tells us that each of the wavelet coefficients at resolution 2 r corresponds to a spatial area of size 2 "r x2 " r in the image /.
- the invention proposes a method making it possible to choose from the 2 "r x2 " ' ' pixels of /, the most representative pixel of this area.
- the detection of salient points in the images can be used, in a non-exhaustive manner:
- the wavelet transformation is a powerful mathematical tool allowing the multi-resolution analysis of a function [1] [2] [3].
- Appendix A for a quick overview of this tool.
- the functions considered are digital images, that is to say discrete two-dimensional functions.
- the processed images are sampled on a discrete grid of n rows and m columns and valued in a luminance space sampled at 256 values.
- n 2 k (kE: Z) and that
- the wavelet transformation of / allows a multi-resolution representation of /.
- the representation of / is given by a coarse image A 2 and by three detail images D 2 l l I, D ⁇ I and D 2l I. Each of these images is of size
- a 2 jl can be calculated by convolving - ⁇ 2 ⁇ +1 / with H in the two dimensions and by subsampling by a factor of two in both dimensions;
- D 2 l j I can be calculated by:
- each wavelet coefficient favors a direction (horizontal, vertical or oblique) depending on the detail image to which it belongs. However, we have chosen not to favor any particular direction and we have therefore merged the information contained in the three wavelet coefficients at 2j (x, y), 2j (x, y), 2j (x, y) whatever the level resolution 2 J and whatever the location (x, y) with 0 ⁇ x ⁇ 2 k + J and 0 ⁇ y ⁇ 2 1 + J.
- Each saliency map S 2 is of size 2 J x 2 I + J.
- the salience of each coefficient at resolution 2 J must take into account the salience of its descendants in the tree of coefficients.
- Equation 1 expression of the salience of a coefficient
- Equation 1 the formulation of the salience of a coefficient given in the Equation 1 is justified.
- each of these coefficients corresponds to an area of size 2x2 coefficients in the map S 2r + 1 .
- Figure 4 illustrates this construction.
- the base of Haar is defined by:
- the indexing of images by content makes it possible to find, from an image database, a set of images visually similar to a given image called a query image. To do this, visual characteristics
- descriptors are extracted from the images and form the signature of the image.
- the signatures of the images belonging to the database are calculated off-line and are stored in the database.
- the engine calculates the signature of the request image and reconciles this signature with the pre-calculated signatures of the database.
- This reconciliation is carried out by calculating the distance between the signature of the request image and the signatures of the database. The images most similar to the query images are then those whose signature minimizes the calculated distance. Figure 7 illustrates this process.
- the whole difficulty of indexing images then consists in determining robust descriptors and distances.
- the distance D (R, I j ) between this signature and the signature of the / th image I j in the database is defined by: D (R, I J ) - 2 1 ⁇ W l S J (f l ) - l, ..., N i where N denotes the number of images in the database and S fJ is defined by:
- weights Wj allow the importance of the descriptors to be modulated in relation to each other.
- the wavelet theory [1] [2] [3] makes it possible to approximate a function (curve, surface, etc.) at different resolutions.
- this theory makes it possible to describe a function in the form of a rough approximation and a series of details making it possible to reconstruct the original function perfectly.
- Such a multi-resolution representation [1] of a function therefore makes it possible to hierarchically interpret the information contained in the function. To do this, this information is reorganized into a set of details appearing at different resolutions. Starting from a sequence of increasing resolutions (r ⁇ ) ⁇ , the details of a function at resolution r 7 are defined as the difference in information between its approximation at resolution ⁇ and its approximation at resolution r. +1 .
- L 2 (R 2 ) denotes the vector space of the functions f (x, y) of two measurable and integrable variables.
- a 2j be the operator which approximates a function f (x) GL 2 (R) h the resolution 2 J (j ⁇ 0) (ief (x) is defined by 2 y samples).
- the expected properties of A lS are as follows:
- ⁇ is a linear operator. If A 2l f (x) represents the approximation def (x) at resolution 2 J , then A 2j f (x) should not be changed when it is approximated again at resolution 2 j .
- a 2j 0A 2j A 2j and shows that the operator A 2J is a projection operator in a vector space V 2J C ⁇ (R). This vector space can be interpreted as the set of all possible approximations at the resolution 2 J of the functions of L 2 (R).
- a 2l f (x) is the most similar to f (x).
- the operator A % s is therefore an orthogonal projection on V 2J .
- the approximation operation is the same at all resolutions.
- the spaces of the approximate functions can be derived from each other by a change of scale corresponding to the difference in resolution: Mj ⁇ Z, f (x) ⁇ V 2J ⁇ »f (2x) ⁇ V ⁇ .
- V 2 j being a vector space containing the approximations of functions of
- a 2J f (f (u) * ⁇ (-2 j u)) (k), kEZ. Since ⁇ (x) is a low-pass filter, -4 ⁇ / can be interpreted as low-pass filtering followed by uniform subsampling.
- a n f be the discrete approximation of / (at resolution n.
- the causality property (cf. section A.3) claims that we can compute A 2j f & from A n f for all j ⁇ k.
- a 2 jf ( u ) ⁇ M k ⁇ 2u) A 2 f (k), Q ⁇ u ⁇ 2 J -l
- the detail function at resolution 2 J is obtained by projecting orthogonally the original function f (x) on the orthogonal complement of F ⁇ in
- 011 can show that -D 2 , / can be obtained by a convolution of the original function / (x) with the high-pass filter ⁇ (x) followed by a subsampling of a factor 2 J :
- V 2J the vector space of the approximations of
- the detail function at resolution 2 y is obtained by an orthogonal projection dcf (x, y) on the complement of V 2 j in V, noted W s .
- ⁇ (x) the wavelet function associated with the scale function ⁇ (x)
- the projection of f (x, y) on these three functions of the base of W 2J gives three detailed functions:
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Processing (AREA)
Abstract
Description
Claims
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| FR0216929 | 2002-12-31 | ||
| FR0216929 | 2002-12-31 | ||
| PCT/FR2003/000834 WO2004068410A1 (fr) | 2002-12-31 | 2003-03-14 | Procédé et dispositif de détection de points d'intérêt dans une image numérique source, programme d'ordinateur et support de données correspondants. |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| EP1579386A1 true EP1579386A1 (fr) | 2005-09-28 |
Family
ID=32799431
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| EP03725291A Withdrawn EP1579386A1 (fr) | 2002-12-31 | 2003-03-14 | Procede et dispositif de detection de points d'interet dans une image numerique source, programme d'ordinateur et support de donees correspondants |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US20060257028A1 (fr) |
| EP (1) | EP1579386A1 (fr) |
| AU (1) | AU2003227837A1 (fr) |
| WO (1) | WO2004068410A1 (fr) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| MX2007002071A (es) * | 2004-08-18 | 2007-04-24 | Nielsen Media Res Inc | Metodos y aparatos para generar firmas. |
| US7970226B2 (en) * | 2007-04-23 | 2011-06-28 | Microsoft Corporation | Local image descriptors |
| US8126275B2 (en) | 2007-04-24 | 2012-02-28 | Microsoft Corporation | Interest point detection |
| US8650402B2 (en) * | 2007-08-17 | 2014-02-11 | Wong Technologies L.L.C. | General data hiding framework using parity for minimal switching |
| ES2322120B1 (es) * | 2007-10-26 | 2010-03-24 | Consejo Superior De Investigaciones Cientificas | Metodo y sistema para analisis de singularidades en señales digitales. |
| US10769247B2 (en) * | 2014-12-04 | 2020-09-08 | Guy Le Henaff | System and method for interacting with information posted in the media |
| CN113313709A (zh) * | 2021-07-14 | 2021-08-27 | 常州微亿智造科技有限公司 | 工业部件的缺陷检测方法和装置 |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5654771A (en) * | 1995-05-23 | 1997-08-05 | The University Of Rochester | Video compression system using a dense motion vector field and a triangular patch mesh overlay model |
| US6144773A (en) * | 1996-02-27 | 2000-11-07 | Interval Research Corporation | Wavelet-based data compression |
| US6157746A (en) * | 1997-02-12 | 2000-12-05 | Sarnoff Corporation | Apparatus and method for encoding wavelet trees generated by a wavelet-based coding method |
| US5923785A (en) * | 1997-03-31 | 1999-07-13 | Interated Systems, Inc. | System and method for compressing data |
| AU7709098A (en) * | 1997-05-30 | 1998-12-30 | Interval Research Corporation | Method and apparatus for wavelet based data compression |
| DE19744648A1 (de) * | 1997-10-09 | 1999-04-15 | Fraunhofer Ges Forschung | Verfahren und Vorrichtung zur Sekundärbilderzeugung und zur schnellen Suche in digitalen Bilddatenbanken |
| KR100284027B1 (ko) * | 1998-12-22 | 2001-03-02 | 서평원 | 웨이블릿 패킷 계수의 재배치방법 |
| KR20000059799A (ko) * | 1999-03-09 | 2000-10-05 | 구자홍 | 웨이브릿 부호화를 이용한 움직임 보상 부호화 장치 및 방법 |
| JP2004509531A (ja) * | 2000-09-12 | 2004-03-25 | コーニンクレッカ フィリップス エレクトロニクス エヌ ヴィ | ビデオ符号化方法 |
| KR100389807B1 (ko) * | 2001-05-30 | 2003-07-02 | 한국과학기술원 | Spiht에 기반한 관심영역의 코딩방법 |
| FR2849329A1 (fr) * | 2002-12-20 | 2004-06-25 | France Telecom | Procede de codage d'une image par ondelettes, procede de decodage, dispositifs, signal et applications correspondantes |
| CN101014966A (zh) * | 2004-06-30 | 2007-08-08 | 彗星视频技术公司 | 包括视频数据压缩的数据压缩方法 |
-
2003
- 2003-03-14 WO PCT/FR2003/000834 patent/WO2004068410A1/fr not_active Ceased
- 2003-03-14 US US10/541,118 patent/US20060257028A1/en not_active Abandoned
- 2003-03-14 AU AU2003227837A patent/AU2003227837A1/en not_active Abandoned
- 2003-03-14 EP EP03725291A patent/EP1579386A1/fr not_active Withdrawn
Non-Patent Citations (1)
| Title |
|---|
| See references of WO2004068410A1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| US20060257028A1 (en) | 2006-11-16 |
| WO2004068410A1 (fr) | 2004-08-12 |
| AU2003227837A1 (en) | 2004-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3707676B1 (fr) | Procédé d'estimation de pose d'une caméra dans le référentiel d'une scène tridimensionnelle, dispositif, système de réalite augmentée et programme d'ordinateur associé | |
| US9117105B2 (en) | 3D face recognition method based on intermediate frequency information in geometric image | |
| Xu et al. | Multi-focus image fusion using fully convolutional two-stream network for visual sensors | |
| Prabhakaran et al. | An automated fracture trace detection technique using the complex shearlet transform | |
| EP2364490A1 (fr) | Dispositif a architecture pipeline de flot de donnees pour la reconnaissance et la localisation d'objets dans une image par balayage de fenetres de detection | |
| EP0960382B9 (fr) | Procede pour reconnaitre dans un catalogue preetabli des etoiles detectees par un senseur stellaire | |
| FR3091355A1 (fr) | Système et procédé d’identification de source radar | |
| Zhang et al. | An improved low rank and sparse matrix decomposition-based anomaly target detection algorithm for hyperspectral imagery | |
| CN116168253A (zh) | 一种遥感影像变化检测方法、装置、设备及可读存储介质 | |
| EP1579386A1 (fr) | Procede et dispositif de detection de points d'interet dans une image numerique source, programme d'ordinateur et support de donees correspondants | |
| Yang et al. | Texture feature extraction of mountain economic forest using high spatial resolution remote sensing images | |
| EP3980926A1 (fr) | Procede de generation de cartes haute resolution a partir de nuages de points | |
| EP1751694B1 (fr) | Procede de caracterisation d'une image numerique et ses applications | |
| Zhang et al. | Learnable reconstruction methods from RGB images to hyperspectral imaging: A survey | |
| Elakkiya et al. | Feature based object recognition using discrete wavelet transform | |
| Ranjan et al. | U-net based MRA framework for segmentation of remotely sensed images | |
| Kavalerov et al. | Three-dimensional Fourier scattering transform and classification of hyperspectral images | |
| Sarkar et al. | Hyperspectral texture synthesis using histogram and power spectral density matching | |
| Mani et al. | Mixed pixel removal in north Tamil Nadu Region for accurate area measurement | |
| Prabu | Canopy removal on satellite images using classification and contrast enhancement | |
| Patil et al. | Performance improvement of face recognition system by decomposition of local features using discrete wavelet transforms | |
| Loiseaux | Multiparameter topological persistence for machine learning | |
| Glazyrina et al. | Deep neural networks for removing clouds and nebulae from satellite images. | |
| Dharini et al. | Multispectral Fusion of Multisensor Image Data Using PCNN | |
| Vu et al. | Designing of wavelet-based processing system for airborne laser scanner segmentation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
| 17P | Request for examination filed |
Effective date: 20050620 |
|
| AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PT RO SE SI SK TR |
|
| AX | Request for extension of the european patent |
Extension state: AL LT LV MK |
|
| DAX | Request for extension of the european patent (deleted) | ||
| 17Q | First examination report despatched |
Effective date: 20080326 |
|
| RIC1 | Information provided on ipc code assigned before grant |
Ipc: G06F 17/30 20060101ALI20090403BHEP Ipc: G06T 5/10 20060101ALI20090403BHEP Ipc: G06T 5/00 20060101ALI20090403BHEP Ipc: G06T 7/00 20060101AFI20090403BHEP |
|
| GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
| STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN |
|
| 18D | Application deemed to be withdrawn |
Effective date: 20091008 |