The synonymy and ambiguity of visual words always exist in the conventional bag of visual words model based object classification methods.Besides

the noisy visual words

so-called visual stop-words will degrade the semantic resolution of visual dictionary.In this article

an image object classification method with homoionym based adaptive soft-assignment and chi-square model is proposed to solve these problems.Firstly

PLSA (Probabilistic Latent Semantic Analysis) is used to analyze the semantic co-occurrence probability of visual words

excavate the latent semantic topics in images

and get the latent topic distributions induced by the words; Secondly

the KL divergence is adopted for measuring semantic distance between visual words

which can get semantically related homoionym; then

adaptive soft-assignment is proposed to realize the soft mapping between SIFT features and some homoionym; finally

the Chi-square model is introduced to eliminate the visual stop-words and reconstruct the visual vocabulary histograms

and moreover

SVM (Support Vector Machine) is used to accomplish object classification.Experimental results indicated that the adverse effects produced by the synonymy and ambiguity of visual words can be overcome effectively

the distinguishability of visual semantic resolution is improved

and the image classification performance is substantially boosted compared with the traditional methods.