The invention relates to a monitoring method based on image features and an LLTSA algorithm for a tool wear state. According to the method, an image texture feature extraction technology is introduced into the field of tool wear fault diagnosis, and monitoring for the tool wear state is realized in combination with three flows of ' signal denoising', 'feature extraction and optimization' and 'mode recognition'. The method comprises the steps of firstly, acquiring an acoustic emission signal in a tool cutting process through an acoustic emission sensor, and carrying out signal denoising processing through an EEMD diagnosis; secondly, carrying out time-frequency analysis on a denoising signal through S transformation, converting a time-frequency image to a contour gray-level map, extracting image texture features through a gray-level co-occurrence matrix diagnosis, and then further carrying out dimensionality reduction and optimization on an extracted feature vector through a scatter matrix and the LLTSA algorithm to obtain a fusion feature vector; and finally training a discrete hidden Markov model of the tool wear state through the fusion feature vector, and establishing a classifier, thereby realizing automatic monitoring and recognition for the tool wear state.