Haopeng Zhang

Breast Histopathological Image Retrieval Based on Latent Dirichlet Allocation

In the field of pathology, whole slide image (WSI) has become the major carrier of visual and diagnostic information. Content-based image retrieval among WSIs can aid the diagnosis of an unknown pathological image by finding its similar regions in WSIs with diagnostic information. However, the huge size and complex content of WSI pose several challenges for retrieval. In this paper, we propose an unsupervised, accurate, and fast retrieval method for a breast histopathological image. Specifically, the method presents a local statistical feature of nuclei for morphology and distribution of nuclei, and employs the Gabor feature to describe the texture information. The latent Dirichlet allocation model is utilized for high-level semantic mining. Locality-sensitive hashing is used to speed up the search. Experiments on a WSI database with more than 8000 images from 15 types of breast histopathology demonstrate that our method achieves about 0.9 retrieval precision as well as promising efficiency. Based on the proposed framework, we are developing a search engine for an online digital slide browsing and retrieval platform, which can be applied in computer-aided diagnosis, pathology education, and WSI archiving and management.

Space object, high-resolution, optical imaging simulation of space-based systems

Acquiring optical images of space objects is one of the most important goals of space-based optical surveillance systems. However, its actually difficult to obtain enough high resolution optical images for space object recognition, attitude measurement and situational awareness. To solve this problem, the imaging model of space-based optical camera and the imaging characteristics of space objects are analyzed in this paper, and a novel method of image simulation is proposed. The high resolution images of space objects simulated by our method are visually similar to the actual imaging results and may provide data support for further research on space technology.

Satellite recognition and pose estimation using homeomorphic manifold analysis

We propose a novel monocular vision-based framework for both satellite recognition and pose estimation, using homeomorphic manifold analysis. We use a unified conceptual manifold to represent continuous pose variation of all satellites in the visual input space, learn nonlinear function mapping from conceptual manifold representation to visual inputs, and decompose discrete category variation in the mapping coefficient space. Experimental results on a simulated image data set show the effectiveness and robustness of our approach.

Factorization of view-object manifolds for joint object recognition and pose estimation

We address multi-view recognition problem by factorizing view-object manifold.We use a common manifold to represent view manifolds of different objects.We use the view manifold deformation for categorization.We extensively experiment to validate the robustness and strength of our approach. Due to large variations in shape, appearance, and viewing conditions, object recognition is a key precursory challenge in the fields of object manipulation and robotic/AI visual reasoning in general. Recognizing object categories, particular instances of objects and viewpoints/poses of objects are three critical subproblems robots must solve in order to accurately grasp/manipulate objects and reason about their environments. Multi-view images of the same object lie on intrinsic low-dimensional manifolds in descriptor spaces (e.g. visual/depth descriptor spaces). These object manifolds share the same topology despite being geometrically different. Each object manifold can be represented as a deformed version of a unified manifold. The object manifolds can thus be parameterized by its homeomorphic mapping/reconstruction from the unified manifold. In this work, we develop a novel framework to jointly solve the three challenging recognition sub-problems, by explicitly modeling the deformations of object manifolds and factorizing it in a view-invariant space for recognition. We perform extensive experiments on several challenging datasets and achieve state-of-the-art results.

3D Reconstruction of Space Objects from Multi-Views by a Visible Sensor

In this paper, a novel 3D reconstruction framework is proposed to recover the 3D structural model of a space object from its multi-view images captured by a visible sensor. Given an image sequence, this framework first estimates the relative camera poses and recovers the depths of the surface points by the structure from motion (SFM) method, then the patch-based multi-view stereo (PMVS) algorithm is utilized to generate a dense 3D point cloud. To resolve the wrong matches arising from the symmetric structure and repeated textures of space objects, a new strategy is introduced, in which images are added to SFM in imaging order. Meanwhile, a refining process exploiting the structural prior knowledge that most sub-components of artificial space objects are composed of basic geometric shapes is proposed and applied to the recovered point cloud. The proposed reconstruction framework is tested on both simulated image datasets and real image datasets. Experimental results illustrate that the recovered point cloud models of space objects are accurate and have a complete coverage of the surface. Moreover, outliers and points with severe noise are effectively filtered out by the refinement, resulting in an distinct improvement of the structure and visualization of the recovered points.

Feature extraction from histopathological images based on nucleus-guided convolutional neural network for breast lesion classification

Abstract Feature extraction is a crucial and challenging aspect in the computer-aided diagnosis of breast cancer with histopathological images. In recent years, many machine learning methods have been introduced to extract features from histopathological images. In this study, a novel nucleus-guided feature extraction framework based on convolutional neural network is proposed for histopathological images. The nuclei are first detected from images, and then used to train a designed convolutional neural network with three hierarchy structures. Through the trained network, image-level features including the pattern and spatial distribution of the nuclei are extracted. The proposed features are evaluated through the classification experiment on a histopathological image database of breast lesions. The experimental results show that the extracted features effectively represent histopathological images, and the proposed framework achieves a better classification performance for breast lesions than the compared state-of-the-art methods.

Ship detection in optical remote sensing images based on deep convolutional neural networks

Abstract. Automatic ship detection in optical remote sensing images has attracted wide attention for its broad applications. Major challenges for this task include the interference of cloud, wave, wake, and the high computational expenses. We propose a fast and robust ship detection algorithm to solve these issues. The framework for ship detection is designed based on deep convolutional neural networks (CNNs), which provide the accurate locations of ship targets in an efficient way. First, the deep CNN is designed to extract features. Then, a region proposal network (RPN) is applied to discriminate ship targets and regress the detection bounding boxes, in which the anchors are designed by intrinsic shape of ship targets. Experimental results on numerous panchromatic images demonstrate that, in comparison with other state-of-the-art ship detection methods, our method is more efficient and achieves higher detection accuracy and more precise bounding boxes in different complex backgrounds.

Optical Image Simulation System for Space Surveillance

Acquiring optical images is a basic task of space based surveillance system. However, these images are hard to obtain in real space condition or are classified for security reason. To solve this problem, a simulation system, based on STK and OpenGL, is established. Using data generated by STK, 3D models of satellites and a star catalogue, we can render the celestial background and space object in OpenGL. Then some post-processing is done to the acquired images to make the final results look real. The simulation results, with high reality and fidelity, can provide data support for space information processing technology, such as object detection, tracking, recognition or for the space surveillance system design.

Airport Detection Using End-to-End Convolutional Neural Network with Hard Example Mining

Deep convolutional neural network (CNN) achieves outstanding performance in the field of target detection. As one of the most typical targets in remote sensing images (RSIs), airport has attracted increasing attention in recent years. However, the essential challenge for using deep CNN to detect airport is the great imbalance between the number of airports and background examples in large-scale RSIs, which may lead to over-fitting. In this paper, we develop a hard example mining and weight-balanced strategy to construct a novel end-to-end convolutional neural network for airport detection. The initial motivation of the proposed method is that backgrounds contain an overwhelming number of easy examples and a few hard examples. Therefore, we design a hard example mining layer to automatically select hard examples by their losses, and implement a new weight-balanced loss function to optimize CNN. Meanwhile, the cascade design of proposal extraction and object detection in our network releases the constraint on input image size and reduces spurious false positives. Compared with geometric characteristics and low-level manually designed features, the hard example mining based network could extract high-level features, which is more robust for airport detection in complex environment. The proposed method is validated on a multi-scale dataset with complex background collected from Google Earth. The experimental results demonstrate that our proposed method is robust, and superior to the state-of-the-art airport detection models.

Ship Recognition Based on Active Learning and Composite Kernel SVM

Aiming at recognizing ship target efficiently and accurately, a novel method based on active learning and the Composite Kernel Support Vector Machines (CK-SVM) is proposed. First, we build a ship recognition dataset which contains the major warship models and massive civil ships. Second, to reduce the cost of manual labeling, active learning algorithm is run to select the most informative and representative samples to label. Finally, we construct a composite-kernel SVM combining shape and texture features to recognize ships. The composite-kernel strategy can enhance the quality of features fusion apparently. Experiments demonstrate that our method not only improves the efficiency of samples selection, but also receives satisfying results.