KR970006423B1 - 신경망을 이용한 영상 패턴 분류 인식 장치 및 방법 - Google Patents
신경망을 이용한 영상 패턴 분류 인식 장치 및 방법 Download PDFInfo
- Publication number
- KR970006423B1 KR970006423B1 KR1019930030983A KR930030983A KR970006423B1 KR 970006423 B1 KR970006423 B1 KR 970006423B1 KR 1019930030983 A KR1019930030983 A KR 1019930030983A KR 930030983 A KR930030983 A KR 930030983A KR 970006423 B1 KR970006423 B1 KR 970006423B1
- Authority
- KR
- South Korea
- Prior art keywords
- input
- image
- complex
- neural network
- invariant
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
- G06V10/451—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters with interaction between the filter responses, e.g. cortical complex cells
- G06V10/454—Integrating the filters into a hierarchical structure, e.g. convolutional neural networks [CNN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biodiversity & Conservation Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (4)
- 물체의 영상을 크기 및 회전 변형에 불변인 형태로 변환시키는 영상 입력 장치와 인공 신경망을 이용하여 입력된 영상패턴을 분류인식하는 장치에 있어서, 입력영상에 대하여 복소-대수 사상을 수행하는 복소-대수 사상 수단(21); 복소-대수 사상의 결과로 발생하는 위치 이동 현상을 보정하기 위해, 이차 신경망을 이용하여 상기 복소-대수 사상 수단(21)의 출력을 위치 이동에 불변인 형태로 변환하는 위치이동 불변 처리수단(23); 및 신경망을 이용하여 상기 위치이동 불변 처리 수단(23)의 결과 출력을 분류 인식하는 수단(25)을 포함하는 것을 특징으로 하는 신경망을 이용한 영상 패턴 분류 인식 장치.
- 제1항에 있어서, 상기 복소-대수 사상 수단(21)은 다수의 광 입력소자를 구비하되, 상기 광 입력 소자가 빛을 받아들이는 샘플링 영역(감광 영역)의 위치는 각 동심원마다 교대로 소정간격 만큼씩 위상을 달리 하도록 배열하고, 상기 각 소자들은 극-지수대 분포를 위해 중심으로부터 가장자리로 동심원을 그리며 배열하고, 상기 동심원의 반지름은 지수적으로 증가시키며, 각 동심원상이 광 입력소자의 수는 동일하게 함과 동시에, 같은 각도 위치에 등각도 간격으로 배열되도록 구성함을 특징으로 하는 신경망을 이용한 영상 패턴 분류 인식 장치.
- 제2항에 있어서, 상기 위치이동 불변 처리 수단(23)은 각각 두 개의 입력소자에 두 입력단이 연결되어 있으며, 상기 두 입력단을 통해 입력되는 값을 곱하여 출력하는 다수의 곱셈 수단(41); 및 상기 다수의 곱셈 수단(41)의 각 출력단에 각각 입력단이 연결되어 있으며, 다수의 입력단을 통해 입력되는 값들을 더하여 출력하는 적어도 하나의 덧셈 수단(42)을 포함하여 구성되는 것을 특징으로 하는 신경망을 이용한 영상 패턴 분류 인식 장치.
- 물체의 영상을 크기 및 회전 변형에 불변인 형태로 변환시키는 영상 입력 장치와 인공 신경망을 이용하여 입력된 영상 패턴을 분류 인식하는 방법에 있어서, 입력 영상에 대하여 복소-대수 사상을 수행하는(71) 제1단계; 상기 제1단계의 복소-대수 사상 결과로 발생하는 위치 이동 현상을 보정하기 위해, 이차 신경망을 이용하여 상기 제1단계(71)의 출력을 이동에 불변인 형태로 변환하는(73) 제2단계; 및 신경망을 이용하여 상기 제2단계(23)의 결과출력을 분류 인식하는(75) 제3단계를 포함하는 것을 특징으로 하는 신경망을 이용한 영상 패턴 분류 인식 방법.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1019930030983A KR970006423B1 (ko) | 1993-12-29 | 1993-12-29 | 신경망을 이용한 영상 패턴 분류 인식 장치 및 방법 |
US08/659,739 US5887078A (en) | 1993-12-29 | 1996-06-06 | Apparatus and method for classifying and recognizing image patterns using neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1019930030983A KR970006423B1 (ko) | 1993-12-29 | 1993-12-29 | 신경망을 이용한 영상 패턴 분류 인식 장치 및 방법 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR950020278A KR950020278A (ko) | 1995-07-24 |
KR970006423B1 true KR970006423B1 (ko) | 1997-04-28 |
Family
ID=19373972
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1019930030983A Expired - Fee Related KR970006423B1 (ko) | 1993-12-29 | 1993-12-29 | 신경망을 이용한 영상 패턴 분류 인식 장치 및 방법 |
Country Status (2)
Country | Link |
---|---|
US (1) | US5887078A (ko) |
KR (1) | KR970006423B1 (ko) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6249606B1 (en) * | 1998-02-19 | 2001-06-19 | Mindmaker, Inc. | Method and system for gesture category recognition and training using a feature vector |
US7009645B1 (en) * | 1999-09-30 | 2006-03-07 | Imec Vzw | Constant resolution and space variant sensor arrays |
US6968081B1 (en) * | 1999-11-15 | 2005-11-22 | Luminus Systems, Inc. | System, method, and apparatus for orienting images |
US20060098887A1 (en) * | 2004-05-19 | 2006-05-11 | Hazem El-Bakry | Mehthod for image conversion |
CN101916382B (zh) * | 2010-07-30 | 2012-05-30 | 广州中医药大学 | 一种植物叶片的图像识别方法 |
CN105772407A (zh) * | 2016-01-26 | 2016-07-20 | 耿春茂 | 一种基于图像识别技术的垃圾分类机器人 |
US10621489B2 (en) | 2018-03-30 | 2020-04-14 | International Business Machines Corporation | Massively parallel neural inference computing elements |
US11270105B2 (en) * | 2019-09-24 | 2022-03-08 | International Business Machines Corporation | Extracting and analyzing information from engineering drawings |
CN115221846A (zh) * | 2022-06-08 | 2022-10-21 | 华为技术有限公司 | 一种数据处理方法及相关设备 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4965725B1 (en) * | 1988-04-08 | 1996-05-07 | Neuromedical Systems Inc | Neural network based automated cytological specimen classification system and method |
US5063604A (en) * | 1989-11-08 | 1991-11-05 | Transitions Research Corporation | Method and means for recognizing patterns represented in logarithmic polar coordinates |
US5351311A (en) * | 1992-07-28 | 1994-09-27 | The United States Of America As Represented By The Secretary Of The Navy | Neural network for detection and correction of local boundary misalignments between images |
US5388164A (en) * | 1992-08-19 | 1995-02-07 | Olympus Optical Co., Ltd. | Method for judging particle agglutination patterns using neural networks |
-
1993
- 1993-12-29 KR KR1019930030983A patent/KR970006423B1/ko not_active Expired - Fee Related
-
1996
- 1996-06-06 US US08/659,739 patent/US5887078A/en not_active Expired - Lifetime
Also Published As
Publication number | Publication date |
---|---|
KR950020278A (ko) | 1995-07-24 |
US5887078A (en) | 1999-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11126888B2 (en) | Target recognition method and apparatus for a deformed image | |
EP3783527A1 (en) | Method and device for identifying object node in image, terminal and computer readable storage medium | |
Stanković et al. | Convolutional neural networks demystified: A matched filtering perspective-based tutorial | |
KR970006423B1 (ko) | 신경망을 이용한 영상 패턴 분류 인식 장치 및 방법 | |
EP1262907A1 (en) | Pattern recognition with hierarchical networks | |
Follmann et al. | A rotationally-invariant convolution module by feature map back-rotation | |
EP0511668B1 (en) | Pattern recognition device and method | |
CN112157657A (zh) | 机械臂定位方法、装置、电子设备及存储介质 | |
Joulain et al. | Learning to build visual categories from perception-action associations | |
CN118522034A (zh) | 基于特征增强多尺度融合策略与角动量机制的多目标跟踪算法 | |
Sheta et al. | 3D object recognition using fuzzy mathematical modeling of 2D images | |
EP0535786B1 (en) | Training neural networks by using invariant features of the input patterns | |
CA2105854C (en) | A method and apparatus for symbol recognition using multidimensional preprocessing and symbol sorting | |
CN114418001A (zh) | 一种基于参数重构网络的字符识别方法及系统 | |
Zu et al. | Generalwise separable convolution for mobile vision applications | |
Nakamura et al. | Recognition of object orientation and shape by a rotation spreading associative neural network | |
Busacca | Graph Neural Network for Event-based Vision | |
Shi | Gabor-type image filtering with cellular neural networks | |
US12339405B1 (en) | Lidar-camera online calibration method and system based on reflectance map | |
CN119578482A (zh) | 基于超表面的光电计算芯片的构建方法和光电计算芯片 | |
Lee et al. | Handwritten numeral recognition based on hierarchically self-organizing learning networks with spatio-temporal pattern representation | |
Inigo et al. | Fast analog architecture for high-order curve recognition | |
Aleksander | Memory networks for practical vision systems | |
CN119539026A (zh) | 一种提升三维点云模型抗旋转干扰性的高效知识蒸馏方法 | |
Teiwes et al. | Paraxial diffractive elements for space-variant linear transforms |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 19931229 |
|
PA0201 | Request for examination |
Patent event code: PA02012R01D Patent event date: 19931229 Comment text: Request for Examination of Application |
|
PG1501 | Laying open of application | ||
G160 | Decision to publish patent application | ||
PG1605 | Publication of application before grant of patent |
Comment text: Decision on Publication of Application Patent event code: PG16051S01I Patent event date: 19970327 |
|
E701 | Decision to grant or registration of patent right | ||
PE0701 | Decision of registration |
Patent event code: PE07011S01D Comment text: Decision to Grant Registration Patent event date: 19970725 |
|
GRNT | Written decision to grant | ||
PR0701 | Registration of establishment |
Comment text: Registration of Establishment Patent event date: 19970806 Patent event code: PR07011E01D |
|
PR1002 | Payment of registration fee |
Payment date: 19970806 End annual number: 3 Start annual number: 1 |
|
PR1001 | Payment of annual fee |
Payment date: 20000113 Start annual number: 4 End annual number: 4 |
|
PR1001 | Payment of annual fee |
Payment date: 20010702 Start annual number: 5 End annual number: 5 |
|
PR1001 | Payment of annual fee |
Payment date: 20020626 Start annual number: 6 End annual number: 6 |
|
PR1001 | Payment of annual fee |
Payment date: 20030715 Start annual number: 7 End annual number: 7 |
|
PR1001 | Payment of annual fee |
Payment date: 20040702 Start annual number: 8 End annual number: 8 |
|
PR1001 | Payment of annual fee |
Payment date: 20050729 Start annual number: 9 End annual number: 9 |
|
PR1001 | Payment of annual fee |
Payment date: 20060711 Start annual number: 10 End annual number: 10 |
|
PR1001 | Payment of annual fee |
Payment date: 20070801 Start annual number: 11 End annual number: 11 |
|
FPAY | Annual fee payment |
Payment date: 20080730 Year of fee payment: 12 |
|
PR1001 | Payment of annual fee |
Payment date: 20080730 Start annual number: 12 End annual number: 12 |
|
LAPS | Lapse due to unpaid annual fee | ||
PC1903 | Unpaid annual fee |