WO2001031582A1 - Procede de traitement d'images en presence de bruit structure et de bruit non-structure - Google Patents
Procede de traitement d'images en presence de bruit structure et de bruit non-structure Download PDFInfo
- Publication number
- WO2001031582A1 WO2001031582A1 PCT/FR2000/003007 FR0003007W WO0131582A1 WO 2001031582 A1 WO2001031582 A1 WO 2001031582A1 FR 0003007 W FR0003007 W FR 0003007W WO 0131582 A1 WO0131582 A1 WO 0131582A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- image
- noise
- points
- structures
- structured
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000012545 processing Methods 0.000 title claims abstract description 11
- 238000002592 echocardiography Methods 0.000 claims description 35
- 238000004458 analytical method Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 8
- 240000005636 Dryobalanops aromatica Species 0.000 claims description 5
- 238000012512 characterization method Methods 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 6
- 230000003628 erosive effect Effects 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 238000012916 structural analysis Methods 0.000 description 5
- 238000002604 ultrasonography Methods 0.000 description 4
- 238000003909 pattern recognition Methods 0.000 description 3
- 238000012285 ultrasound imaging Methods 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 2
- 210000003754 fetus Anatomy 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 230000036244 malformation Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241000001036 Bromelia serra Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000916 dilatatory effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000006740 morphological transformation Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/755—Deformable models or variational models, e.g. snakes or active contours
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
Definitions
- the invention relates to a method for
- the invention finds applications in the fields of ultrasound imaging and electromagnetic imaging for analyzing 2D or 3D images and providing representations of the object captured in images,
- the invention can be applied in the medical field, for the diagnosis, by ultrasound, of a disease or else
- the invention can also be applied in the nuclear field, for the inspection of a fast neutron reactor vessel in service, in order to visualize the submerged metal structures,
- the image acquired by such a device must then be interpreted by the user to diagnose the state of the object.
- the sonographer must know how to interpret ultrasound images to detect a malformation of the fetus or any other abnormality.
- HOUGH transform Another method for analyzing structured noise is the HOUGH transform, which is described in particular by H. MAITRE in “an overview of the HOUGH transformation", Signal processing, 2, n ° 4, 1984, or even in “ A survery of the HOUGH Transform and its extensions for curve detection ”, by A. lANNINO and SD SHAPIRO, Pattern Recognition and Image Processing, pages 32 - 38, 1978.
- This method consists in transforming a problem of pattern recognition into a problem of finding maxima.
- the object of the invention is precisely to propose a method for processing intensity images representative of an object whose contours are disturbed by structured noise and unstructured noise.
- specular echo for a transmitter-receiver couple, the specular point on a given surface is that which defines the shortest path between the transmitter and the receiver passing through this point of the surface (FERMAT principle). This point is actually associated with a spot characteristic of the imaging system (opening of the antennas) and of the geometry of the object surface at the theoretical specular point, creating a cloud of points in the volume; - diffracted echo: when the object has sharp edges, a diffraction phenomenon occurs.
- the reflected wave propagates in privileged directions, thus contributing locally to highlights;
- - backscattered echo this echo only exists for rough structures, the roughness scale of which is close to that of the wavelength;
- echoes are likely to be found in the digital volume formed after the acquisition of the image. Some of these echoes are semantically and visually rich in information: they are what allow the human brain to reconstruct the scene captured in images. These are, in particular, diffracted and backscattered echoes.
- the image processing proposed by the invention is precisely based on the identification of these different types of echoes.
- the method of the invention seeks to eliminate the background noise while retaining the backscattered echoes, to eliminate the phantom echoes (namely the structured noise) while retaining the information relevant given by the backscattered and diffracted echoes and to correctly dissociate the specular echoes from the diffracted echoes.
- the invention relates to a method for processing a 2D or 3D image representative of an object whose contours are disturbed by structured noise and unstructured noise, characterized in that it consists in extracting from the image, the active contour (or relevant contour) of the object by the following steps: a) elimination, on the initial image, of unstructured noise having an amplitude close to that of the contours of the object to be extracted, by thresholding, by a maximum of entropy, a unimodal histogram representative of the distribution of the amplitudes in the image, thus providing a binarized image; b) analysis of the structured noise of the image, from the binarized image, by eliminating the fine structures and by filling the holes of the thick structures extracted in step a) to provide an image with significant structures; c) recognition of the edges of the object by characterizing, on the image with significant structures, the structured noise associated with diffraction echoes and the structured noise associated with specular echoes, by extracting and locating the diffraction echoes
- the characterization of the structured noise associated with diffraction echoes is carried out on the basis of a parameter ⁇ measuring the rate of change of the minima in depth r m ⁇ n extracted for each azimuth ⁇ ⁇ . of a connected component CC, with
- N is the number of points CC
- ⁇ indicating the orientation of the characteristic points
- step d) of optimizing the contour is carried out by the following function:
- step a) consists in applying the KAPUR method (described later) to amplitude images, in which the entropies are determined from a number of states fixed a priori.
- FIG. 2 shows the structures to be extracted in step b) of the method of the invention
- FIG. 3 represents an example of an object immersed in an acquisition volume, an object whose surface representation is sought to be determined; and FIGS. 4A - 4F represent the different images obtained, for the object of FIG. 3, during the process of the invention.
- the method of the invention generally consists in enabling automatic detection
- the method of the invention consists, from a digital image
- the background cells essentially contain background noise (low-frequency unstructured noise) and cannot be used to characterize the surfaces of objects. information
- the invalidated cells do not characterize the ultrasonic information visually and semantically rich, but can however contain it.
- the method of the invention therefore proposes to identify the different types of echoes by characterization and classification of the different cells of the digital volumes obtained after acquisition of the ultrasonic image of the object studied. This is achieved through the following four steps: a) an analysis of unstructured noise, i.e. background noise; b) an analysis of the structured noise, that is to say a detection of the multiple reflections and of the signature of the object; c) recognition of the edges of the object from the image obtained in b); and d) recognition of the surfaces of the object from the raw image (or initial image) and from the images obtained in steps b) and c).
- unstructured noise i.e. background noise
- b) an analysis of the structured noise that is to say a detection of the multiple reflections and of the signature of the object
- recognition of the edges of the object from the image obtained in b recognition of the edges of the object from the image obtained in b
- recognition of the surfaces of the object from the raw image (or initial image) and from the images obtained in steps b
- the images processed by the method of the invention can be two-dimensional or three-dimensional. They can be of the ultrasonic or electromagnetic type. However, to simplify the description, the invention will be described only in the case of a two-dimensional ultrasonic image described in polar coordinates.
- the images processed by the method of the invention are intensity images or, more precisely, amplitude images in the sense that what is displayed corresponds to an intensity which codes for the amplitude.
- FIG. 1 schematically represents the different stages of the method of the invention.
- Block a corresponds to the analysis of unstructured noise; after this step a) an image II is obtained on which the diffracted and specular echoes are physically characterized.
- Block b corresponds to the analysis of structured noises which makes it possible to obtain, on an image 12, the geometric characterization of these diffracted and specular echoes.
- Block c represents the operation of recognizing the edges of the object by determining the invalid areas of image 12 and the characteristic points of the outline of the object.
- block d represents the recognition of the surfaces of the object, with the determination of the active contour of the object.
- block e represents the geometric model representing the surface of the object studied.
- Step a) consists in physically characterizing the unstructured noise. This can be of two types:
- this step a) is to characterize the background cells, that is to say the cells which essentially contain background noise, namely unstructured low frequency noise; these cells cannot be used to characterize the surfaces of the object studied.
- this step a) consists of a binarization adapted to a digital volume.
- This binarization is achieved by a thresholding of a unimodal histogram by maximum of entropy, cut by cut.
- the invention proposes to use the known KAPUR method to eliminate background noise in quantized images in gray levels and to adapt it to intensity images.
- the KAPUR method is described in the document entitled “a new method for Gray-Level Picture Thresholding using the Entropy of the histogram”, by JN KAPUR et al., Published in computer vision, graphies, and image processing, n ° 29, 273 - 285, 1985. According to the invention, the method of
- KAPUR has been modified so that it can be adapted to intensity images, not quantified in gray levels.
- the modification relates to the intra-class posterior entropy which is calculated on a number of states fixed a priori, so as to modify the quantification of the intra-class histograms as a function of the intensity binarization threshold.
- Step b) of the method of the invention consists of a structural analysis of the image of the object, or analysis of structured noise. Unlike unstructured noise which is characterized physically, structured noise is characterized geometrically. The analysis of structured noise is therefore made from the binarized image obtained in step a).
- Structural analysis can be carried out according to two distinct methods: by a mathematical morphology or by a HOUGH transform.
- the HOUGH transform designates a method which makes it possible to detect the presence of forms belonging to a family of simple parametric curves (in 2D) or of simple parametric surfaces (in 3D) and this, from a binary image or a set of characteristic points previously extracted. It is a statistical method making it possible to transform a problem of pattern recognition into a problem of finding maxima.
- a priori we use a simple form, called a structuring element, to extract shapes, two-dimensional or three-dimensional, interpretable. It is an inductive approach which consists in exploiting what one is looking for. The displacement of this structuring element in the structured set supposes an inclusion relation between the definition spaces of the two sets.
- the structural analysis method used is mathematical morphology, which makes it possible to detect globally triangular structures associated with edge echoes and rather rectangular structures associated with specular echoes.
- the mathematical morphology allows, by an opening operation, to soften the contours and, in particular, to remove small structures.
- This opening operation conventionally consists in eroding a set of cells with a structuring element, then in dilating the whole resulting from this erosion using the same structuring element.
- a classic morphological closure operation consists of expansion, then erosion by a structuring element.
- the closure helps fill gaps; the image resulting from this transformation contains the initial shape.
- the process of the invention proposes using erosion with a small structuring element to eliminate both the remaining background noise and the backscattering information processed subsequently. There remain, then, only the structures associated with the diffraction streaks and the specular streaks. In order to plug the holes observed mainly in the diffraction streaks, the invention proposes to use an expansion by a larger 3D structuring element. Taking such a structuring element makes it possible to extract solid and significant structures with the aim of discriminating specular echoes - diffracted echoes.
- diffracted echoes contain topological information, unlike specular echoes. It is therefore important to be able to discriminate the structures resulting from specular echoes from the structures resulting from diffracted echoes in order to be able to determine, among all the structures, those which contain important information, namely information relating to the edges of the object.
- this recognition of the edges of the object is carried out by detecting the depth minima which correspond to characteristic points, then closing, or modeling, all of these characteristic points.
- a diffraction structure is generally triangular while a specular structure is generally rectangular. It is therefore important to properly characterize the triangular structures.
- Each triangle is characterized by its vertices: the vertex of minimum depth corresponds to a corner of the front face of the object, the other vertex of neighboring polar angle corresponds to the corner of the rear face located on the same side face as the front corner. The position of the third vertex relative to the other two indicates on which side to look for the surface information.
- FIG. 2 represents precisely such rectangular R and triangular structures Tl and T2.
- the triangular structure Tl shows that we have to look
- the discrimination between triangular and rectangular components is then carried out thanks to a first parameter ⁇ measuring the rate of variation of the minima in depth r rain extracted for each azimuth ⁇ ⁇ from a connected component CC:
- N is the number of CC points.
- the front face of the redundancy structure (vis-à-vis the incident waves) is almost plane and the connected component is interpreted as the significant drag of a specular echo. If ⁇ is close to 0.5, the front face is inclined and corresponds to the hypotenuse of the desired diffraction triangle.
- ⁇ indicates whether the lower limit in depth of a connected diffraction component is located on the side of the azimuths lower or higher than the median azimuth of the component:
- i a is the azimuth of the point of minimum depth of CC
- iamix and iamax are, respectively, the minimum and maximum azimuths of the studied component.
- ⁇ and ⁇ are the two characteristic parameters of 2D connected diffraction components from which it is possible to extract the point of minimum depth labeled at + 1 depending on whether the surface to be extracted is to the right or to the left of the point.
- the method of the invention then proposes a step d) of recognizing the surfaces of the object.
- This recognition of surfaces is established from the image obtained in c) of the edges of the object and from the image of significant structures obtained after step b).
- this surface recognition is translated by the detection of plane curves from snap points (or characteristic points) and, in 3D, by the detection of surfaces from left snap curves.
- this step d) firstly consists in initializing the “active” contours of the object, in other words, the actual contours of the object. For this, we consider the characteristic points of the linked list determined in step c) as the ends of the curves to be extracted and we look for other attachment points for the initial contours, also called interior points, which do not belong at the edges determined in step c).
- the points in the linked list to match must be of opposite labels.
- the succession of two points of the same label means that one outline hides another. This simplification results in the exclusive treatment of the pairs of points, of opposite labels, successive in the linked list.
- the missing edge is initialized by the point of shallowest depth.
- the optimization of the active contours consists in choosing a deformable model which integrates the structure of the volume cuts: an active contour is sought in the form of a polar 2D graph, with coordinates (p, ⁇ ).
- the optimization method, according to the invention, is based on the active contour stated from the EULER-LAGRANGE theorem with the following functional:
- the adopted discretization constrains the points of the model to remain on their line in depth. Only a local approximation of the intensities on the depth lines will guide the displacement of the points against the internal regulating force, which acts more on a regularity according to the azimuths.
- the advantage of this constraint is to obtain a good distribution of points even if the difference between the points is not strictly constant.
- Boundary conditions are fixed by p ( ⁇ o), p '( ⁇ o), p ( ⁇ ), p' ( ⁇ ), which guarantee the uniqueness of the solution of the differential system of order 4.
- R (t) [p (0, t), p ( ⁇ , t), ..., p ( ⁇ ⁇ t)],
- F (t) - is the derivative at each point of the active contour a P of a cubic B-spline approximating each line in depth crossed by the curve, and A is a pentadiagonal matrix in the case of open active contours (with ends free or fixed), symmetrical band:
- h is the average distance between two points of the active contour at time t.
- Figures 3 and 4A to 4F show an example of application of the method of the invention. More specifically, Figure 3 shows a flat plate which is sought to obtain a good representation. This flat plate has a length of 0.8 m, a width of 0.7 m and a thickness of 0.02 m. For the example considered, it is placed 2 m from the imaging system.
- the digital volumes shown are limited to the areas of good performance of the imaging system, namely over an area ranging from + 15 ° in azimuths with a step of 0.25 °, from -5 ° to + 1 ° in sites with also a step of 0.25 °, and a field in depth ranging from 1.98 m to 2.1 m discretized on 101 points.
- FIGS. 4A to 4F show the different representations of the object obtained during the process. More specifically, FIG. 4A represents the ultrasonic image of the planar plate, seen from above. FIG. 4B represents the image obtained after step a) of analysis of the unstructured noise.
- FIGS. 4C and 4D represent the binarized images obtained, respectively, during step b) and at the end of this step b) of analysis of structured noise.
- FIG. 4C corresponds to the image obtained after the erosion operation of image 4B by small structuring elements
- FIG. 4D represents the image obtained after expansion by a large structuring element.
- FIG. 4E represents the flat plate after step c) of recognition of the edges of the object
- FIG. 4F shows the active contour of the flat plate, obtained at the end of the process of the invention.
Abstract
Description
Claims
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP00974589A EP1151414A1 (fr) | 1999-10-28 | 2000-10-27 | Procede de traitement d'images en presence de bruit structure et de bruit non-structure |
JP2001534090A JP2003512874A (ja) | 1999-10-28 | 2000-10-27 | 構造化ノイズ及び非構造化ノイズの存在で像を処理する方法 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
FR99/13501 | 1999-10-28 | ||
FR9913501A FR2800491B1 (fr) | 1999-10-28 | 1999-10-28 | Procede de traitement d'images en presence de bruit structure et de bruit non-structure |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2001031582A1 true WO2001031582A1 (fr) | 2001-05-03 |
Family
ID=9551477
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/FR2000/003007 WO2001031582A1 (fr) | 1999-10-28 | 2000-10-27 | Procede de traitement d'images en presence de bruit structure et de bruit non-structure |
Country Status (5)
Country | Link |
---|---|
EP (1) | EP1151414A1 (fr) |
JP (1) | JP2003512874A (fr) |
FR (1) | FR2800491B1 (fr) |
RU (1) | RU2001121202A (fr) |
WO (1) | WO2001031582A1 (fr) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113916979A (zh) * | 2021-09-17 | 2022-01-11 | 秒针信息技术有限公司 | 工件缺陷检测方法、装置、系统及计算机可读存储介质 |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6071260B2 (ja) * | 2012-06-13 | 2017-02-01 | キヤノン株式会社 | 被検体情報取得装置および情報処理方法 |
KR101777948B1 (ko) * | 2016-02-19 | 2017-09-12 | 정영규 | 엔트로피와 배경변화율 차이점을 이용한 주요 객체 자동 검출 장치 |
AU2016404824B2 (en) * | 2016-04-25 | 2019-08-15 | Telefield Medical Imaging Limited | Method and device for measuring spinal column curvature |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4729019A (en) * | 1985-10-18 | 1988-03-01 | Cgr Ultrasonic | Method and device for generating images from ultrasonic signals obtained by echography |
US5360006A (en) * | 1990-06-12 | 1994-11-01 | University Of Florida Research Foundation, Inc. | Automated method for digital image quantitation |
US5669387A (en) * | 1992-10-02 | 1997-09-23 | Kabushiki Kaisha Toshiba | Ultrasonic diagnosis apparatus and image displaying system |
-
1999
- 1999-10-28 FR FR9913501A patent/FR2800491B1/fr not_active Expired - Fee Related
-
2000
- 2000-10-27 WO PCT/FR2000/003007 patent/WO2001031582A1/fr not_active Application Discontinuation
- 2000-10-27 JP JP2001534090A patent/JP2003512874A/ja not_active Withdrawn
- 2000-10-27 RU RU2001121202/09A patent/RU2001121202A/ru not_active Application Discontinuation
- 2000-10-27 EP EP00974589A patent/EP1151414A1/fr not_active Withdrawn
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4729019A (en) * | 1985-10-18 | 1988-03-01 | Cgr Ultrasonic | Method and device for generating images from ultrasonic signals obtained by echography |
US5360006A (en) * | 1990-06-12 | 1994-11-01 | University Of Florida Research Foundation, Inc. | Automated method for digital image quantitation |
US5669387A (en) * | 1992-10-02 | 1997-09-23 | Kabushiki Kaisha Toshiba | Ultrasonic diagnosis apparatus and image displaying system |
Non-Patent Citations (1)
Title |
---|
CIOS K J ET AL: "AN EDGE EXTRACTION TECHNIQUE FOR NOISY IMAGES", IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING,US,IEEE INC. NEW YORK, vol. 37, no. 5, 1 May 1990 (1990-05-01), pages 520 - 524, XP000138448, ISSN: 0018-9294 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113916979A (zh) * | 2021-09-17 | 2022-01-11 | 秒针信息技术有限公司 | 工件缺陷检测方法、装置、系统及计算机可读存储介质 |
Also Published As
Publication number | Publication date |
---|---|
EP1151414A1 (fr) | 2001-11-07 |
FR2800491B1 (fr) | 2001-11-23 |
JP2003512874A (ja) | 2003-04-08 |
RU2001121202A (ru) | 2003-06-27 |
FR2800491A1 (fr) | 2001-05-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Nguyen et al. | Free-form anisotropy: A new method for crack detection on pavement surface images | |
Merazi-Meksen et al. | Mathematical morphology for TOFD image analysis and automatic crack detection | |
EP2146315B1 (fr) | Procédé et dispositif de filtrage du bruit de speckle dans des images SAR | |
CN106778668B (zh) | 一种联合ransac和cnn的鲁棒的车道线检测方法 | |
FR2763721A1 (fr) | Dispositif electronique de traitement d'images pour la detection de variations dimensionnelles | |
Malkiel et al. | Automated scanning and measurements of particle distributions within a holographic reconstructed volume | |
EP0732668A1 (fr) | Méthode d'extraction de contours utilisant une analyse multi-fractale | |
Shahrezaei et al. | Fractal analysis and texture classification of high-frequency multiplicative noise in SAR sea-ice images based on a transform-domain image decomposition method | |
Davies et al. | Evaluating unsupervised methods to size and classify suspended particles using digital in-line holography | |
EP3343201A1 (fr) | Procédé de comptage et de caractérisation de particules dans un fluide en mouvement | |
CN111127533A (zh) | 基于神经网络的多特征融合砂轮磨削性能预测方法 | |
EP2872871B1 (fr) | Procédé et système de reconstruction de propriétés optiques d'objets diffractants baignant dans un milieu liquide | |
FR2922029A1 (fr) | Dispositif et methode de detection d'objet | |
FR2632071A1 (fr) | Echographe ultrasonore a bruit d'interference reduit | |
EP1151414A1 (fr) | Procede de traitement d'images en presence de bruit structure et de bruit non-structure | |
FR2955666A1 (fr) | Procede d'estimation de defauts dans un objet et dispositif de mise en oeuvre | |
Nevis et al. | Advantages of three-dimensional electro-optic imaging sensors | |
Forbes et al. | Estimating fruit volume from digital images | |
Osman et al. | An automated data processing method dedicated to 3D ultrasonic non destructive testing of composite pieces | |
Wang et al. | Seafloor classification based on deep-sea multibeam data—Application to the southwest Indian Ridge at 50.47° E | |
CN112330667A (zh) | 一种基于形态学的激光条纹中心线提取方法 | |
JP5773935B2 (ja) | シーンにおけるオブジェクトを分類する方法 | |
Guevara et al. | Segmentation and morphometry of histological sections using deformable models: a new tool for evaluating testicular histopathology | |
EP3903282B1 (fr) | Méthode de segmentation d'une image | |
FR3013850A1 (fr) | Procede de reconstruction d'une surface d'une piece |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A1 Designated state(s): JP RU US |
|
AL | Designated countries for regional patents |
Kind code of ref document: A1 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2000974589 Country of ref document: EP |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
ENP | Entry into the national phase |
Ref country code: JP Ref document number: 2001 534090 Kind code of ref document: A Format of ref document f/p: F |
|
WWE | Wipo information: entry into national phase |
Ref document number: 09869369 Country of ref document: US |
|
WWP | Wipo information: published in national office |
Ref document number: 2000974589 Country of ref document: EP |
|
WWW | Wipo information: withdrawn in national office |
Ref document number: 2000974589 Country of ref document: EP |