本文对皮肤肿瘤目标识别技术进行研究。首先利用阈值分割方法对皮损区域进行分割;然后,依据皮肤肿瘤早期诊断ABCD准则,对皮损区域提取了颜色、纹理和形状等特征,并基于相关性分析对所提取的特征进行优选;最后采用组合BP神经网络模型实现了皮肤肿瘤目标的分类识别。本文方法在黄色人种皮肤镜图像上进行实验,结果表明,该方法具有更高的分类精度,敏感度和特异度分别达到了93.3%和96.7%,识别结果令人满意。 In this paper, the target of skin tumor identification technology research. Firstly, the segmentation method was used to segment the lesion area. Then, the color, texture and shape of the lesion area were extracted according to the ABCD criteria of skin tumor early diagnosis, and the extracted features were optimized based on the correlation analysis. Finally, The combined BP neural network model was used to realize the classification and recognition of skin tumor targets. The experimental results show that this method has higher classification accuracy, sensitivity and specificity of 93.3% and 96.7% respectively, and the results are satisfactory.