It is light-sensitive and sick robustness by using the image segmentation method to extract the size distribution of froth image. It is robust to lighting conditions by using wavelet texture analysis to extract froth image texture features because of the multi-scale statistical property of this method, but are not able to reflect froth morphology characteristics directly. Therefore, a method of equivalent size distribution characteristics of flotation froth image based on wavelet multiscale analysis is proposed. A kind of new flotation froth image features called equivalent size distribution features are extracted, which are used in copper flotation froth image classification. The experimental results show that the extracted equivalent size distribution features can distinguish froth image corresponding to three different working conditions.