Object detection based on local feature matching and segmentation

This paper proposes a novel automatic geo-spatial object recognition algorithm for high resolution satellite imaging. The proposed algorithm consists of two main steps; a hypothesis generation step with a local feature-based algorithm and a verification step with a shape-based approach. In the hypothesis generation step, a set of hypothesis for possible object locations is generated, aiming lower missed detections and higher false-positives by using a Bag of Visual Words type approach. In the verification step, the foreground objects are first extracted by a semi-supervised image segmentation algorithm, utilizing detection results from the previous step, and then, the shape descriptors for segmented objects are utilized to prune out the false positives. Based on simulation results, it can be argued that the proposed algorithm achieves both high precision and high recall rates as a result of taking advantage of both the local feature-based and the shape-based object detection approaches. The superiority of the proposed method is due to the ability of minimization of false alarm rate and since most of the object shapes contain more characteristic and discriminative information about their identity and functionality.

Density-aware generative algorithms learning from positive examples have verified high recall for visual object detection, but such generative methods suffer from excessive false positives which leads to low precision. Inspired by the recent success of detection-recognition pipeline with deep neural networks, this paper proposes a two-step framework by training a generative detector with positive samples first and then utilising a discriminative model to get rid of false positives in those detected bounding box candidates by the generative detector. Evidently, the discriminative model can be viewed as a post-processing step which improves the robustness by distinguishing true positives from false positives that confuse the generative detector. We exemplify the proposed approach on public ImageNet classes to demonstrate the significant improvement on precision while using only positive examples in training.

Establishing structural or functional relationship between sequences, for instance to infer the structural class of an unannotated protein, is a key task in biological analysis. Protein sequences undergo complex transformations such as mutation, insertion and deletion during the evolutionary process and typically share low sequence similarity on the superfamily level, making the task for remote homology detection based on primary sequence only very challenging. Based on previous studies stating that knowledge based on only a subset of critical positions and the preferred symbols on such positions are sufficient for remote homology detection, we present a series of works, each enforcing different notion of sparsity, to recover such critical positions. We first start with a generative model and present the sparse profile hidden Markov models. Such generative approach recovers some critical patterns and motivates the need for discriminative learning. In our second study, we present a discriminative approach to recover such critical positions and the preferred symbols. In our third study, we address the issue of very few positive training examples, accompanied by a large number of negative training examples, which is typical in many remote homology detection task. Such issue motivates the need for semi-supervised learning. However, though containing abundant useful and critical information, large uncurated sequence databases also contain a lot of noise, which may compromise the quality of the classifiers. As a result, we present a systematic and biologically motivated framework for semi-supervised learning with large uncurated sequence databases. Combined with a very fast string kernel, our method not only realizes rapid and accurate remote homology detection and show state-of-the-art performance, but also recovers some critical patterns conserved in superfamilies.

BackgroundThe rapid growth of biomedical literature requires accurate text analysis and text processing tools. Detecting abbreviations and identifying their definitions is an important component of such tools. Most existing approaches for the abbreviation definition identification task employ rule-based methods. While achieving high precision, rule-based methods are limited to the rules defined and fail to capture many uncommon definition patterns. Supervised learning techniques, which offer more flexibility in detecting abbreviation definitions, have also been applied to the problem. However, they require manually labeled training data.MethodsIn this work, we develop a machine learning algorithm for abbreviation definition identification in text which makes use of what we term naturally labeled data. Positive training examples are naturally occurring potential abbreviation-definition pairs in text. Negative training examples are generated by randomly mixing potential abbreviations with unrelated potential definitions. The machine learner is trained to distinguish between these two sets of examples. Then, the learned feature weights are used to identify the abbreviation full form. This approach does not require manually labeled training data.ResultsWe evaluate the performance of our algorithm on the Ab3P, BIOADI and Medstract corpora. Our system demonstrated results that compare favourably to the existing Ab3P and BIOADI systems. We achieve an F-measure of 91.36% on Ab3P corpus, and an F-measure of 87.13% on BIOADI corpus which are superior to the results reported by Ab3P and BIOADI systems. Moreover, we outperform these systems in terms of recall, which is one of our goals.

Local feature matching using deep learning: A survey

The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only few positive training examples are available for each location, we propose a new approach to calibrate all the per-location SVM classifiers using only the negative examples. The calibration we propose relies on a significance measure essentially equivalent to the p-values classically used in statistical hypothesis testing. Experiments are performed on a database of 25,000 geotagged street view images of Pittsburgh and demonstrate improved place recognition accuracy of the proposed approach over the previous work.

For hyper-rectangles in $$\mathbb{R}^{d}$$ Auer (1997) proved a PAC bound of $$O(\frac{1}{\varepsilon}(d+\log \frac{1}{\delta}))$$ , where $$\varepsilon$$ and $$\delta$$ are the accuracy and confidence parameters. It is still an open question whether one can obtain the same bound for intersection-closed concept classes of VC-dimension $$d$$ in general. We present a step towards a solution of this problem showing on one hand a new PAC bound of $$O(\frac{1}{\varepsilon}(d\log d + \log \frac{1}{\delta}))$$ for arbitrary intersection-closed concept classes, complementing the well-known bounds $$O(\frac{1}{\varepsilon}(\log \frac{1}{\delta}+d\log \frac{1}{\varepsilon}))$$ and $$O(\frac{d}{\varepsilon}\log \frac{1}{\delta})$$ of Blumer et al. and (1989) and Haussler, Littlestone and Warmuth (1994). Our bound is established using the closure algorithm, that generates as its hypothesis the intersection of all concepts that are consistent with the positive training examples. On the other hand, we show that many intersection-closed concept classes including e.g. maximum intersection-closed classes satisfy an additional combinatorial property that allows a proof of the optimal bound of $$O(\frac{1}{\varepsilon}(d+\log \frac{1}{\delta}))$$ . For such improved bounds the choice of the learning algorithm is crucial, as there are consistent learning algorithms that need $$\Omega(\frac{1}{\varepsilon}(d\log\frac{1}{\varepsilon} +\log\frac{1}{\delta}))$$ examples to learn some particular maximum intersection-closed concept classes.

Hierarchical learning strategy in semantic relation extraction

A common obstacle in effective learning of visual concept classifiers is the scarcity of positive training examples due to expensive labeling cost. This paper explores the sampling of weakly tagged web images for concept learning without human assistance. In particular, ontology knowledge is incorporated for semantic pooling of positive examples from ontologically neighboring concepts. This effectively widens the coverage of the positive samples with visually more diversified content, which is important for learning a good concept classifier. We experiment with two learning strategies: aggregate and incremental. The former strategy re-trains a new classifier by combining existing and newly collected examples, while the latter updates the existing model using the new samples incrementally. Extensive experiments on NUS-WIDE and VOC 2010 datasets show very encouraging results, even when comparing with classifiers learnt using expert labeled training examples.

CorMatcher: A corners-guided graph neural network for local feature matching

This paper presents a novel method to retrieve images by learning the embedded visual concept from a set of given examples. Through a user's relevance feedback, the visual concept can be effectively learned to classify images which contain common visual entities. The learning process is started by providing a set of either positive or negative training examples and is then interactively adjusted according to the user's relevance feedback. In contrast to traditional methods, the proposed method utilizes a novel way to overcome the under-training problem which is frequently suffered in the learning process. Since no time-consuming optimization process is involved, the proposed method learns the visual concepts extremely fast. Therefore, the target concept can be learned on-line and is user-adaptable for effective retrieval of image contents. Experimental results are provided to prove the superiority of the proposed method.

Graphical models are often used to represent and recognize activities. Purely unsupervised methods (such as HMMs) can be trained automatically but yield models whose internal structure - the nodes - are difficult to interpret semantically. Manually constructed networks typically have nodes corresponding to sub-events, but the programming and training of these networks is tedious and requires extensive domain expertise. In this paper, we propose a semi-supervised approach in which a manually structured, Propagation Network (a form of a DBN) is initialized from a small amount of fully annotated data, and then refined by an EM-based learning method in an unsupervised fashion. During node refinement (the M step) a boosting-based algorithm is employed to train the evidence detectors of individual nodes. Experiments on a variety of data types - vision and inertial measurements - in several tasks demonstrate the ability to learn from as little as one fully annotated example accompanied by a small number of positive but non-annotated training examples. The system is applied to both recognition and anomaly detection tasks.

A method of object detecting based on local contour learning and matching is proposed. Firstly, the representative images are obtained through unsupervised clustering to be as templates. The local contour information of template is extracted and generalized as the template feature, at the same time, codebook dictionary of local contour is built up. Secondly, based on codebook dictionary, using simple sliding-window mechanism and vote algorithm to select initial candidate object windows, the final object windows are got from initial candidate windows based on template feature matching. Experimental results demonstrate that our proposed approach is able to consistently identify and accurately detect the objects with better performance than the existing methods.

This paper describes a new method for pedestrian detection. The focus of the proposed method is to enhance the number of detected pedestrian and to achieve high accuracy with low rates of false negative detection. The method has two stages: the first stage detects pedestrians using part based detector (poselet) while the second stage further detects people by combine top-down recognition with bottom-up image segmentation. For feature extraction, Pyramid Histogram of Orientation Gradient (PHOG) and Shape Context (SC) are used. The proposed method was tested on a popular pedestrian detection benchmark dataset “INRIA person data set” and experimental results show that the detection method achieves high accuracy with low rates of false negative detection.

We present a novel approach to measuring distances between objects in images, suitable for information-rich object representations which simultaneously capture several properties in each image pixel. Multiple spatial fuzzy sets on the image domain, unified in a vector-valued fuzzy set, are used to model such representations. Distance between such sets is based on a novel point-to-set distance suitable for vector-valued fuzzy representations. The proposed set distance may be applied in, e.g., template matching and object classification, with an advantage that a number of object features are simultaneously considered. The distance measure is of linear time complexity w.r.t. the number of pixels in the image. We evaluate the performance of the proposed measure in template matching in presence of noise, as well as in object detection and classification in low resolution Transmission Electron Microscopy images.