摘要
针对自选餐厅结账中人工计价的效率问题,文中提出了一种基于颜色特征的食物类别识别算法。该算法通过边缘投影提取目标区域,再基于Lab颜色模型对食物图像聚类分割,利用HSV颜色模型获取各类子区域的颜色特征,并基于区域颜色识别食物的种类。分别针对1类和3类食物的各30幅图像进行了仿真实验和统计分析。结果表明,算法识别准确率可达95.6%,识别速度最快只需0.119 s。
n view of the efficiency of manual pricing in the checkout of the cafeteria,a new recognition algorithm based on color feature is proposed in this paper. In the algorithm,the edge projection and extract the target area,the segmentation of food image clustering based on Lab color model using HSV color model to obtain the color features of all kinds of regional,and based on the regional color recognition of food species. Simulations and statistical analysis for a class of 30 images and 3 kinds of food. The results show that the accuracy of the algorithm can reach 95. 6% and the fastest speed of recognition is only 0. 119 s.
出处
《电子科技》
2016年第6期1-4,7,共5页
Electronic Science and Technology
基金
国家自然科学基金资助项目(61005034)
河北省自然科学基金资助项目(F2012203185)
