Image recognition system and method

The invention relates to an image recognition system and method. The system comprises an image reading module, a median filtering module, a gradient direction angle division and calibration module, a region non-maximum suppression module, a self-adaptive dynamic threshold generation module, an image edge point calibration module, an output module and a comparison module. According to the invention, modeling is carried out on the improved Sobel operator edge refining algorithm, so that a simulation system oriented to the improved Sobel operator edge refining FPGA is realized; not only are the accuracy and continuity of image edge information effectively improved, but also a reliable verification method and a simulation system are provided for the image edge refinement FPGA design; the invention has the advantages of being extensible, easy to transplant, high in universality and visual. 本发明涉及一种图像识别系统和方法，该系统包括：图像读取模块、中值滤波模块、梯度方向角划分与标定模块、区域非极大值抑制模块、自适应动态阈值产生模块、图像边缘点标定模块、输出模块与比对模块组成。本发明通过对改进Sobel算子边缘细化算法建模，实现了面向改进