With the development of the very large scale integration circuit (VLSI), multi-core processors have been developing fast and provide a novel approach to meet the requirements of modern complex computing. Real-time SAR imaging is always a hard problem to deal with since the huge amount of data and complex processing. Therefore, we design a schedulable and scalable multi-core parallel architecture based on FPGA and map the fundamental Chirp Scaling algorithm to the system. The design of the master control core makes the system highly extensible and the dedicated computing cores are designed to accelerate the process. In addition, the system can meet the real-time requirements, and it performs well in the resource utilization and the FPGA chip takes up a small space as well.

In image classification, visual separability between different object categories is highly uneven, and some categories are more difficult to distinguish than others. Such difficult categories demand more dedicated classifiers. However, existing deep convolutional neural networks (CNN) are trained as flat N-way classifiers, and few efforts have been made to leverage the hierarchical structure of categories. In this paper, we introduce hierarchical deep CNNs (HD-CNNs) by embedding deep CNNs into a two-level category hierarchy. An HD-CNN separates easy classes using a coarse category classifier while distinguishing difficult classes using fine category classifiers. During HDCNN training, component-wise pretraining is followed by global fine-tuning with a multinomial logistic loss regularized by a coarse category consistency term. In addition, conditional executions of fine category classifiers and layer parameter compression make HD-CNNs scalable for largescale visual recognition. We achieve state-of-the-art results on both CIFAR100 and large-scale ImageNet 1000-class benchmark datasets. In our experiments, we build up three different two-level HD-CNNs, and they lower the top-1 error of the standard CNNs by 2:65%, 3:1%, and 1:1%.

While discriminative visual element mining has been introduced before, in this paper we present an approach that requires minimal annotation in both training and test time. Given only a bounding box localization of the foreground objects, our approach automatically transforms the input images into a roughly-aligned pose space and discovers the most discriminative visual fragments for each category. These fragments are then used to learn robust classifiers that discriminate between very similar categories under challenging conditions such as large variations in pose or habitats. The minimal required input, is a critical characteristic that enables our approach to generalize over visual domains where expert knowledge is not readily available. Moreover, our approach takes advantage of deep networks that are targeted towards fine-grained classification. It learns mid-level representations that are specific to a category and generalize well across the category instances at the same time. Our evaluations demonstrate that the automatically learned representation based on discriminative fragments, significantly outperforms globally extracted deep features in classification accuracy.

We present a new feature representation method for scene text recognition problem, particularly focusing on improving scene character recognition. Many existing methods rely on Histogram of Oriented Gradient (HOG) or part-based models, which do not span the feature space well for characters in natural scene images, especially given large variation in fonts with cluttered backgrounds. In this work, we propose a discriminative feature pooling method that automatically learns the most informative sub-regions of each scene character within a multi-class classification framework, whereas each sub-region seamlessly integrates a set of low-level image features through integral images. The proposed feature representation is compact, computationally efficient, and able to effectively model distinctive spatial structures of each individual character class. Extensive experiments conducted on challenging datasets (Chars74K, ICDAR'03, ICDAR'11, SVT) show that our method significantly outperforms existing methods on scene character classification and scene text recognition tasks.

In this paper we present a framework for logo retrieval in natural images. Color-localized spatial masks are used as an alternative to computationally expensive spatial verification techniques like RANSAC. First, keypoints are detected using traditional techniques such as the SIFT detector. Local masks are defined around each keypoint that take its scale and orientation information into account. To exploit inherent color information presented in brand logos, ordered color histograms are extracted from masked regions. A separate vocabulary is constructed for both SIFT descriptors (visual word) and color histograms (color word). For faster matching during runtime, a two-stage cascaded index is designed, which maps the visual word and color word tuple to a list of relevant images. This list is finally re-ranked with BoW cosine similarity to generate relevant matches for the input query. To demonstrate the efficacy of our method, we conduct experiments on two popular logo datasets: Flickr27 and Flickr32. Our experimental results illustrate State-of-the-art retrieval performance on these datasets with potential for added speed and a lower memory footprint as indicated by the low response ratio.

We describe a completely automated large scale visual recommendation system for fashion. Our focus is to efficiently harness the availability of large quantities of online fashion images and their rich meta-data. Specifically, we propose two classes of data driven models in the Deterministic Fashion Recommenders (DFR) and Stochastic Fashion Recommenders (SFR) for solving this problem. We analyze relative merits and pitfalls of these algorithms through extensive experimentation on a large-scale data set and baseline them against existing ideas from color science. We also illustrate key fashion insights learned through these experiments and show how they can be employed to design better recommendation systems. The industrial applicability of proposed models is in the context of mobile fashion shopping. Finally, we also outline a large-scale annotated data set of fashion images Fashion-136K) that can be exploited for future research in data driven visual fashion.

The rapid increase in number of high quality mobile cameras have opened up an array of new problems in mobile vision. Mobile cameras are predominantly monocular and are devoid of any sense of depth, making them heavily reliant on 2D image processing. Understanding 3D structure of scenes being imaged can greatly improve the performance of existing vision/graphics techniques. In this regard, recent availability of large scale RGB-D datasets beg for more effective data driven strategies to leverage the scale of data. We propose a depth recovery mechanism “im2depth”, that is lightweight enough to run on mobile platforms, while leveraging the large scale nature of modern RGB-D datasets. Our key observation is to form a basis (dictionary) over the RGB and depth spaces, and represent depth maps by a sparse linear combination of weights over dictionary elements. Subsequently, a prediction function is estimated between weight vectors in RGB to depth space to recover depth maps from query images. A final superpixel post processor aligns depth maps with occlusion boundaries, creating physically plausible results. We conclude with thorough experimentation with four state of the art depth recovery algorithms, and observe an improvement of over 6.5 percent in shape recovery, and over 10cm reduction in average L1 error.

As the amount of user generated content on the internet grows, it becomes ever more important to come up with vision systems that learn directly from weakly annotated and noisy data. We leverage a large scale collection of user generated content comprising of images, tags and title/captions of furniture inventory from an e-commerce website to discover and categorize learnable visual attributes. Furniture categories have long been the quintessential example of why computer vision is hard, and we make one of the first attempts to understand them through a large scale weakly annotated dataset. We focus on a handful of furniture categories that are associated with a large number of fine-grained attributes. We propose a set of localized feature representations built on top of state-of-the-art computer vision representations originally designed for fine-grained object categorization. We report a thorough empirical characterization on the visual identifiability of various fine-grained attributes using these representations and show encouraging results on finding iconic images and on multi-attribute prediction.

In online peer-to-peer commerce places where physical examination of the goods is infeasible, textual descriptions, images of the products, reputation of the participants, play key roles. Visual image is a powerful channel to convey crucial information towards e-shoppers and influence their choice. In this paper, we investigate a well-known online marketplace where over millions of products change hands and most are described with the help of one or more images. We present a systematic data mining and knowledge discovery approach that aims to quantitatively dissect the role of images in e-commerce in great detail. Our goal is two-fold. First, we aim to get a thorough understanding of impact of images across various dimensions: product categories, user segments, conversion rate. We present quantitative evaluation of the influence of images and show how to leverage different image aspects, such as quantity and quality, to effectively raise sale. Second, we study interaction of image data with other selling dimensions by jointly modeling them with user behavior data. Results suggest that "watch" behavior encodes complex signals combining both attention and hesitation from buyer, in which image still holds an important role when compared to other selling variables, especially for products for which appearance is important. We conclude on how these findings can benefit sellers in a high competitive online e-commerce market.

With the explosion of mobile devices with cameras, online search has moved beyond text to other modalities like images, voice, and writing. For many applications like Fashion, image-based search offers a compelling interface as compared to text forms by better capturing the visual attributes. In this paper we present a simple and fast search algorithm that uses color as the main feature for building visual search. We show that low level cues such as color can be used to quantify image similarity and also to discriminate among products with different visual appearances. We demonstrate the effectiveness of our approach through a mobile shopping application\footnote{eBay Fashion App available at https://itunes.apple.com/us/app/ebay-fashion/id378358380?mt=8 and eBay image swatch is the feature indexing millions of real world fashion images}. Our approach outperforms several other state-of-the-art image retrieval algorithms for large scale image data.

Active learning (AL) seeks to interactively construct a smaller training data set that is the most informative and useful for the supervised classification task. Based on the multiview Adaptive Maximum Disagreement AL method, this study investigates the principles and capability of several approaches for the view generation for hyperspectral data classification, including clustering, random selection, and uniform subset slicing methods, which are then incorporated with dynamic view updating and feature space bagging strategies. Tests on Airborne Visible/Infrared Imaging Spectrometer and Hyperion hyperspectral data sets show excellent performance as compared with random sampling and the simple version support vector machine margin sampling, a state-of-the-art AL method.

In order to focus on the hard classes in a multi-class classification task, a critical class oriented query strategy is proposed, which combines the concepts of "guided learning" and "active learning". In conjunction with the SVM classifier, hard pair classes are first identified based on the instability of the classification hyperplane, whereby category level guidance for which class should be queried next is sought and then provided to the active query system. Samples with higher possibility of belonging to these classes as evaluated by the current learner are queried first. Two methods are proposed. The first method (SVM-CC) simply conducts category level query. The second method (SVM- CCMS) further incorporates the uncertainty measurement based on the idea of margin sampling, so as to directly focus on the most informative samples from the identified "trouble classes". Experiments are conducted on AVIRIS and Hyperion data. Results are compared to Random Sampling and the state-of-the-art active learning method SVM based simple margin sampling SVMMS. Superior performance is obtained, whereas hard classes are successfully identified first.

A multi-view based active learning method (AMDWVE) is proposed as a means to optimally construct the training set for supervised classification of hyperspectral data, thereby reducing the effort required to acquire ground reference data. The method explores the intrinsic multi-view information embedded in hyperspectral data. By adaptively and quantitatively measuring the disagreement level of different views, the learner focuses on samples with higher confusion, rapidly reducing the version space and improving the learning speed. Classification confidence of each view towards each class is also obtained in the learning process and used to compensate for view insufficiency. Experiments show excellent performance on both unlabeled and unseen data from two sets of hyperspectral image data with 10 classes acquired by AVIRIS, as compared to random sampling and the state-of-the-art SVMSIMPLE.

This correspondence paper studies face recognition by using hyperspectral imagery in the visible light bands. The spectral measurements over the visible spectrum have different discriminatory information for the task of face identification, and it is found that the absorption bands related to hemoglobin are more discriminative than the other bands. Therefore, feature band selection based on the physical absorption characteristics of face skin is performed, and two feature band subsets are selected. Then, three methods are proposed for hyperspectral face recognition, including whole band (2D)2PCA, single band (2D)2PCA with decision level fusion, and band subset fusion-based (2D)2PCA. A simple yet efficient decision level fusion strategy is also proposed for the latter two methods. To testify the proposed techniques, a hyperspectral face database was established which contains 25 subjects and has 33 bands over the visible light spectrum (0.4-0.72 μm). The experimental results demonstrated that hyperspectral face recognition with the selected feature bands outperforms that by using a single band, using the whole bands, or, interestingly, using the conventional RGB color bands.