Image Recognition Method Based on Edge Features and Artificial Neural Network

• Main Authors: LI,ROU-YI, 李柔誼
• Other Authors: Chang, Chi-Feng
• Format: Others
• Language: zh-TW
• Published: 2019
• Online Access: http://ndltd.ncl.edu.tw/handle/u34qgr

碩士 === 國立高雄科技大學 === 機械工程系 === 107 === This study image feature recognition is based on the edge line.Two methods are proposed for image recognition in the study.The first is a sample comparison, and the second is a neural network training.Both methods use text modeling blocks to test samples.The image edge feature is created by the gradient after the binarized image.In the sample comparison, the edge features of the sample must be established first.Find the gradient of the each pixel,and use the edge feature of the sample and the gradient angle of the image to judge the similarity.In the neural network, it is performed based on the image edge features of the training data.In order to highlight the edge features of the image, this study trains the pixel position, the X and Y direction gradient of the edge feature pixel .Thereby improving the recognition rate of image recognition. Learned from the experimental results.Both pattern recognition methods are not limited by the text modeling blocks pattern, the position and placement direction.The average recognition rate of the edge feature sample comparison method is 98%.The average recognition rate of the edge feature neural network is 59%.Because the neural network identification rate of the edge feature is low, this study attempts to perform neural network training based on HSV and RGB value in the pixel, image binarization, grayscale value as training data.The recognition rates are 79%, 88%, 96%, and 88%, respectively.Among them, HSV is the best.