Heterogeneous image transformation

Heterogeneous image transformation (HIT) plays an important role in both law enforcements and digital entertainment. Some available popular transformation methods, like locally linear embedding based, usually generate images with lower definition and blurred details mainly due to two defects: (1) these approaches use a fixed number of nearest neighbors (NN) to model the transformation process, i.e., K-NN-based methods; (2) with overlapping areas averaged, the transformed image is approximately equivalent to be filtered by a low pass filter, which filters the high frequency or detail information. These drawbacks reduce the visual quality and the recognition rate across heterogeneous images. In order to overcome these two disadvantages, a two step framework is constructed based on sparse feature selection (SFS) and support vector regression (SVR). In the proposed model, SFS selects nearest neighbors adaptively based on sparse representation to implement an initial transformation, and subsequently the SVR model is applied to estimate the lost high frequency information or detail information. Finally, by linear superimposing these two parts, the ultimate transformed image is obtained. Extensive experiments on both sketch-photo database and near infrared–visible image database illustrates the effectiveness of the proposed heterogeneous image transformation method.

► Proposed the unified notion for various images: heterogeneous image transformation.
► Took sketch-photo and visible-near infrared image transformations as examples.
► Proposed a two-step method consisting of sparse neighbor selection and SVR.
► Applied objective image quality assessment metric to evaluate image’s quality.