AUTOMATIC SELECTION AND ADJUSTMENT OF FEATURES FOR IMAGE CLASSIFICATION(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
Recently, image classification has been an important task in various fields. Generally, the performance of image classification is not good without the adjustment of image features. Therefore, it is desired that the way of automatic feature extraction. In this paper, we propose an image classification method which adjusts image features automatically. We assume that texture features are useful in image classification tasks because natural images are composed of several types of texture. Thus, the classification accuracy rate is improved by using distribution of texture features. We obtain texture features by calculating image features from a current considering pixel and its neighborhood pixels. And we calculate image features from distribution of textures feature. Those image features are adjusted to image classification tasks using Genetic Algorithm. We apply proposed method to classifying images into "head" or "non-head" and "male" or "female".
- 2009-01-05
著者
-
Saiki Kenji
Graduate School Of Environment And Information Sciences Yokohama National University
-
Nagao Tomoharu
Graduate School Of Environment And Information Sciences Yokohama National University
-
Nagao Tomoharu
Graduate School Of Environment And Information Science Yokohama National University
関連論文
- COLOR RECOGNITION OF IMAGES USING A CATEGORICAL COLOR PERCEPTION MODEL(INTERNATIONAL Workshop on Advanced Image Technology 2008)
- AUTOMATIC SELECTION AND ADJUSTMENT OF FEATURES FOR IMAGE CLASSIFICATION(International Workshop on Advanced Image Technology 2009)
- Dynamic Ant Programming for Automatic Construction of Programs
- Genetic Matrix Algorithm ; Simultaneous Optimization of Structure and Numerical Parameters
- POSITION AND POSTURE ESTIMATION OF 3D-OBJECT USING COLOR AND DISTANCE INFORMATION(International Workshop on Advanced Image Technology 2009)
- A Template Matching Method Based on Marker-Controlled Watershed Segmentation(Image Recognition, Computer Vision)
- D-12-22 Characters Recognition in Scene Images Based on Shape Feature Vectors
- EXTRACTION OF ILLUMINATION EFFECTS FROM NATURAL IMAGES WITH COLOR TRANSITION MODEL(INTERNATIONAL Workshop on Advanced Image Technology 2008)
- D-12-113 Particle Swarm Optimization for Template Matching
- STABLE WEIGHT ESTIMATION FROM X-RAY IMAGE(International Workshop on Advanced Image Technology 2007)
- FAST TRAINING OF LARGE DATA SET ON SOM-SVM FOR PATTERN RECOGNITION(INTERNATIONAL Workshop on Advanced Image Technology 2008)