Binarisation of various images by detecting local thresholds with a validation test

The threshold method is one of the most important stages in the image pattern recognition chain when the object to be modeled does not contain texture. The authors present an efficient threshold method for a variety of images. It is based on the automatic detection of the different local thresholds of the image, taking into consideration the local properties of each histogram (unimodal, bimodal, or multimodal). Validation criteria are used in obtaining each optimal threshold. The method was tested on several classes of images, representing various stages of difficulty. This method has proved effective compared with other methods which are generally only valid for specific applications. The processing results obtained preserve the details of each object. Thus, the improvement of the threshold image contributes to a better pattern recognition