Nanjing University of Information Science and Technology

About: Nanjing University of Information Science and Technology is a education organization based out in Nanjing, China. It is known for research contribution in the topics: Precipitation & Aerosol. The organization has 14129 authors who have published 17985 publications receiving 267578 citations. The organization is also known as: Nan Xin Da.

Fusing Heterogeneous Features From Stacked Sparse Autoencoder for Histopathological Image Analysis

Abstract: In the analysis of histopathological images, both holistic (e.g., architecture features) and local appearance features demonstrate excellent performance, while their accuracy may vary dramatically when providing different inputs. This motivates us to investigate how to fuse results from these features to enhance the accuracy. Particularly, we employ content-based image retrieval approaches to discover morphologically relevant images for image-guided diagnosis, using holistic and local features, both of which are generated from the cell detection results by a stacked sparse autoencoder. Because of the dramatically different characteristics and representations of these heterogeneous features (i.e., holistic and local), their results may not agree with each other, causing difficulties for traditional fusion methods. In this paper, we employ a graph-based query-specific fusion approach where multiple retrieval results (i.e., rank lists) are integrated and reordered based on a fused graph. The proposed method is capable of combining the strengths of local or holistic features adaptively for different inputs. We evaluate our method on a challenging clinical problem, i.e., histopathological image-guided diagnosis of intraductal breast lesions, and it achieves $91.67\%$ classification accuracy on $120$ breast tissue images from $40$ patients.

Low Rank Component Induced Spatial-Spectral Kernel Method for Hyperspectral Image Classification

Abstract: Kernel methods, e.g., composite kernels (CKs) and spatial-spectral kernels (SSKs), have been demonstrated to be an effective way to exploit the spatial-spectral information nonlinearly for improving the classification performance of hyperspectral image (HSI). However, these methods are always conducted with square-shaped window or superpixel techniques. Both techniques are likely to misclassify the pixels that lie at the boundaries of class, and thus a small target is always smoothed away. To alleviate these problems, in this paper, we propose a novel patch-based low rank component induced spatial-spectral kernel method, termed LRCISSK, for HSI classification. First, the latent low-rank features of spectra in each cubic patch of HSI are reconstructed by a low rank matrix recovery (LRMR) technique, and then, to further explore more accurate spatial information, they are used to identify a homogeneous neighborhood for the target pixel (i.e., the centroid pixel) adaptively. Finally, the adaptively identified homogenous neighborhood which consists of the latent low-rank spectra is embedded into the spatial-spectral kernel framework. It can easily map the spectra into the nonlinearly complex manifolds and enable a classifier (e.g., support vector machine, SVM) to distinguish them effectively. Experimental results on three real HSI datasets validate that the proposed LRCISSK method can effectively explore the spatial-spectral information and deliver superior performance with at least 1.30% higher OA and 1.03% higher AA on average when compared to other state-of-the-art classifiers.

A copy-move forgery detection method based on CMFD-SIFT

Abstract: A very common way of image tampering is the copy-move attack. When creating a copy-move forgery, it is often necessary to add or remove important objects from an image. To carry out forensic analysis of such images, various copy-move forgery detection (CMFD) methods have been developed in the literatures. In recent years, many feature-based CMFD approaches have emerged due to its excellent robustness to various transformations. However there is still place to improve performance further. Many of them would suffer from the problem of insufficient matched key-points while performing on the mirror transformed forgeries. Furthermore, many feature-based methods might hardly expose the tempering when the forged region is of uniform texture. In this paper, a novel feature-based CMFD method is proposed. Key-points are detected by using a modified SIFT-based detector. A novel key-points distribution strategy is developed for interspersing the key-points evenly throughout an image. Finally, key-points are descripted by an improved SIFT descriptor which is enhanced for the CMFD scenario. Extensive experimental results are presented to confirm the efficacy.