Classification of tomato impact bruise using hyperspectral imaging based on spatial-spectral method

Tomatoes have various drop impacts on post-harvest process, which causes the quality deterioration. It is required to evaluate impact injuries quickly in a non-destructive method. Hyperspectral image is commonly of with multimodal classes and ambiguous class boundary, and spatially adaptive classification of land cover with hyperspectral image is one of challenging problems in accurate classification image community. As hyperspectral image includes many interesting objects whereas each object contains variant spectral signature and the discrimination among them is less efficient. This paper presents a new spatial-spectral fusion method, which extracts patch analysis and combines spectral features to perform fruit quality classification. In spectral features, a method of tomato quality classification based on mean-square-error curve fitting and peak-feature matching is presented. It extracts peakfeatures from known drop injury tomatoes ' spectra and unknown tomato samples spectra to compute their similarity values through multiple similarity measures, respectively. Then, the unknown sample is assigned by selecting the known quality tomato with the largest similarity value. At last, in comparison with the proposed method and the method such as partial-least square discriminate analysis (PLS-DA), support vector machine (SVM), the result shows the practicality and accuracy of the proposed method.