FIGURE ALPHABET HYPOTHESIS INSPIRED NEURAL NETWORK RECOGNITION MODEL(International Workshop on Advanced Image Technology 2009)
スポンサーリンク
概要
- 論文の詳細を見る
The object recognition mechanism of human being is not well understood yet. On research of animal experiment using an ape, however, neurons that respond to simple shape (e.g. circle, triangle, square and so on) were found. And Hypothesis has been set up as human being may recognize object as combination of such simple shapes. That mechanism is called Figure Alphabet Hypothesis, and those simple shapes are called Figure Alphabet. As one way to research object recognition algorithm, we focused attention to this Figure Alphabet Hypothesis. Getting idea from it, we proposed the feature extraction algorithm for object recognition. In this paper, we described recognition of binarized images of multifont alphabet characters by the recognition model which combined three-layered neural network in the feature extraction algorithm. First of all, we calculated the difference between the learning image data set and the template by the feature extraction algorithm. The computed finite difference is a feature quantity of the feature extraction algorithm. We had it input the feature quantity to the neural network model and learn by backpropagation(BP method). We had the recognition model recognize the unknown image data set and found the correct answer rate. To estimate the performance of the contriving recognition model, we had the unknown image data set recognized by a conventional neural network. As a result, the contriving recognition model showed a higher correct answer rate than a conventional neural network model. Therefore the validity of the contriving recognition model could be proved. We'll plan the research a recognition of natural image by the contriving recognition model in the future.
- 2009-01-05
著者
-
Ohira Ryoji
Department of Information Media and Environment Graduate School of Environment and Information Scien
-
Saiki Kenji
Department of Information Media and Environment Graduate School of Environment and Information Scien
-
Nagao Tomoharu
Department of Information Media and Environment Graduate School of Environment and Information Scien
-
Ohira Ryoji
Department Of Information Media And Environment Graduate School Of Environment And Information Scien
-
Nagao Tomoharu
Yokohama National Univ. Kanagawa Jpn
関連論文
- FIGURE ALPHABET HYPOTHESIS INSPIRED NEURAL NETWORK RECOGNITION MODEL(International Workshop on Advanced Image Technology 2009)
- HXCS and Its Application to Financial Time Series Forecasting
- Buy-Sell Strategy Model Construction with Hybrid XCS
- PARTICLE SWARM OPTIMIZATION FOR TEMPLATE MATCHING(International Workshop on Advanced Image Technology 2007)
- A CATEGORICAL COLOR PERCEPTION MODEL USING STRUCTURED NEURAL NERWORK(International Workshop on Advanced Image Technology 2006)
- A Categorical Perception Model in consideration for Color Constancy (Medical Imaging and Computer Vision)(International Workshop On Advanced Image Technology (IWAIT2004))
- PT-ACTIT; Parameter Tunable - Automatic Construction of Tree-structural Image Transformation (Image Processing and Coding)(International Workshop On Advanced Image Technology (IWAIT2004))
- FAST TREE-STRUCTURAL IMAGE PROCESSING USING GPU(International Workshop on Advanced Image Technology 2007)
- FINDING OPTIMIZED OBJECT ALPHABET USING GA(INTERNATIONAL Workshop on Advanced Image Technology 2008)
- AUTOMATIC EXTRACTION OF INTERNAL ORGANS REGION FROM 3D PET IMAGE DATA USING 3D-ACTIT(International Workshop on Advanced Image Technology 2006)
- 3D medical image processing using 3D-ACTIT : Automatic Construction of Tree-structural Image Transformation (Computer Vision, Medical Applications and Networked MM)(International Workshop On Advanced Image Technology (IWAIT2004))
- AUTOMATIC CONSTRUCTION OF ABNORMAL SIGNAL EXTRACTION PROCESSING FROM 3D DIFFUSION WEIGHTED IMAGE(International Workshop on Advanced Image Technology 2007)
- SIMULATING RUBBER ACTUATOR IN PICTURE ANALYSIS WITH NEURAL NETWORK (Image Processing and Coding)(International Workshop On Advanced Image Technology (IWAIT2004))
- GENETIC IMAGE NETWORK (GIN) : AUTOMATICALLY CONSTRACTION OF IMAGE PROCESSING ALGORITHM(International Workshop on Advanced Image Technology 2007)
- AN ADAPTIVE OPTIMIZATION TECHNIQUE AND ITS APPLICATION TO POSTURE ESTIMATION(INTERNATIONAL Workshop on Advanced Image Technology 2008)