The invention discloses an image detection method and device. The method comprises the following steps of detecting highlight area pixels in a to-be-detected image through a dual threshold algorithm; counting a grey level histogram of pixels except the highlight area pixels in the to-be-detected image and constructing a Gaussian mixture model for gray level distribution of the pixels except the highlight area pixels; utilizing an expectation-maximization algorithm to carry out parameter estimation on the Gaussian mixture model of the pixels except the highlight area pixels; and determining whether the pixels except the highlight area pixels belong to a target detection area in the to-be-detected image based on parameter values of the Gaussian mixture model, which are obtained through parameter estimation. According to the image detection method provided by the embodiments of the invention, an interested area in the image can be accurately detected.