Cross-modal retrieval method and device based on hash algorithm and neighborhood graph

The invention discloses a cross-modal retrieval method and device based on a hash algorithm and a neighborhood graph, and the method comprises the steps: obtaining a multi-modal original sample, minimizing a residual value obtained before and after feature transformation of the multi-modal original sample to acquire a minimized residual value; learning potential association among the multi-modal original samples according to a collaborative matrix decomposition method, and calculating according to the potential association to obtain semantic consistency among modals of the multi-modal originalsamples; adopting popular learning of a neighborhood graph to calculate and obtain semantic consistency in modals of the multi-modal original sample; and minimizing the residual value, the semantic consistency between the modals and the semantic consistency in the modals, and combining regularization calculation avoiding overfitting to obtain an objective function. According to the embodiment ofthe invention, the target