基于不变矩和支持向量机的小样本图像识别

Method of image recognition based on statistics can achieve fine performance only if it’s provided with large numbers of samples. In practice however, sometimes it’s impossible to obtain so many samples, which may results in the poor recognition-performance because lacking of information. Consequently in the paper an arithmetic that combines wavelet moment with Support Vector Machine (SVM) is established. The arithmetic grounds on existing sample-information to acquire optimal solution, as a result, it’s applicable to analyze the instance of small sample. In the first place, extracting Hu moment, Zernike moment and wavelet moment of tank images with restricted sample amount and then distinguishing them through neural network and SVM respectively. The experimental results demonstrate that the arithmetic is superior to others on recognition efficiency in the case of small sample.