Abstract

Optic nerve head (ONH) segmentation problem is of interest for automated glaucoma assessment. Although various segmentation methods have been proposed in the recent past, it is difficult to evaluate and compare the performance of individual methods due to a lack of a benchmark dataset. The assessment involves segmentation of optic disk and cup region within the ONH. In this paper, we present a comprehensive dataset of retinal images of both normal and glaucomatous eyes with manual segmentations from multiple human experts. The dataset also provides expert opinion on an image representing a normal or glaucomatous eye and on the presence of notching in an image. Several state of the art methods are assessed against this dataset using cup to disc diameter ratio (CDR), area and boundary-based evaluation measures. These are presented to aid benchmarking of new methods. A supervised, notch detection method based on the segmentation results is also proposed and its assessment results are included for benchmarking.

Abstract

We propose a fast and accurate method for counting themitotic figures from histopathological slides using regenerative random forest. Our method performs automatic feature selection in an integratedmanner with classification. The proposed random forest assigns a weight to each feature (dimension) of the feature vector in a novel manner based on the importance of the feature (dimension). The forest also assigns amis classification-based penalty term to each tree in the forest. The trees are then regenerated to make a new population of trees (new forest)and only the more important features survive in the new forest. The feature vector is constructed from domain knowledge using the intensity features of nucleus, features of nuclear membrane and features of the possible stroma region surrounding the cell. The use of domain knowledge improves the classification performance. Experiments show at least 4%improvement in F-measure with an improvement in time complexity on the MITOS dataset from ICPR 2012 grand challenge

Abstract

With a view to provide a user-friendly interface for designing, training and developing deep learning frameworks, we have developed Expresso, a GUI tool written in Python. Expresso is built atop Caffe, the open-source, prize-winning framework popularly used to develop Convolutional Neural Networks. Expresso provides a convenient wizard-like graphical interface which guides the user through various common scenarios--data import, construction and training of deep networks, performing various experiments, analyzing and visualizing the results of these experiments. The multi-threaded nature of Expresso enables concurrent execution and notification of events related to the aforementioned scenarios. The GUI sub-components and inter-component interfaces in Expresso have been designed with extensibility in mind. We believe Expresso's flexibility and ease of use will come in handy to researchers, newcomers and seasoned alike, in their explorations related to deep learning.

Abstract

Freehand line sketches are an interesting and unique form of visual representation. Typically, such sketches are studied and utilized as an end product of the sketching process. However, we have found it instructive to study the sketches as sequentially accumulated composition of drawing strokes added over time. Studying sketches in this manner has enabled us to create novel sparse yet discriminative sketch-based representations for object categories which we term category-epitomes. Our procedure for obtaining these epitomes concurrently provides a natural measure for quantifying the sparseness underlying the original sketch, which we term epitome-score. We construct and analyze category-epitomes and epitome-scores for freehand sketches belonging to various object categories. Our analysis provides a novel viewpoint for studying the semantic nature of object categories.

Abstract

Automatic annotation of an audio or a music piece with multiple labels helps in understanding the composition of a music. Such meta-level information can be very useful in applications such as music transcription, retrieval, organization and personalization. In this work, we formulate the problem of annotation as multi-label classification which is considerably different from that of a popular single (binary or multi-class) label classification. We employ both the nearest neighbour and max-margin (SVM) formulations for the automatic annotation. We consider K-NN and SVM that are adapted for multi-label classification using one-vs-rest strategy and a direct multi-label classification formulation using ML-KNN and M3L. In the case of music, often the signatures of the labels (e.g. instruments and vocal signatures) are fused in the features. We therefore propose a simple feature augmentation technique based on non …

Abstract

The mismatch between the training data and the test data distributions is a challenging issue while designing many practical computer vision systems. In this paper, we propose a domain adaptation technique to tackle this issue. We are interested in a domain adaptation scenario where source domain has large amount of labeled examples and the target domain has large amount of unlabeled examples. We align the source domain subspace with the target domain subspace in order to reduce the mismatch between the two distributions. We model the subspace using Locality Preserving Projections (LPP). Unlike previous subspace alignment approaches, we introduce a strategy to effectively utilize the training labels in order to learn discriminative subspaces. We validate our domain adaptation approach by testing it on two different domains, i.e. handwritten and printed digit images. We compare our approach with …

Abstract

In this paper, we describe a classifier based retrieval scheme for efficiently and accurately retrieving relevant documents. We use SVM classifiers for word retrieval, and argue that the classifier based solutions can be superior to the OCR based solutions in many practical situations. We overcome the practical limitations of the classifier based solution in terms of limited vocabulary support, and availability of training data. In order to overcome these limitations, we design a one-shot learning scheme for dynamically synthesizing classifiers. Given a set of SVM classifiers, we appropriately join them to create novel classifiers. This extends the classifier based retrieval paradigm to an unlimited number of classes (words) present in a language. We validate our method on multiple datasets, and compare it with popular alternatives like OCR and word spotting. Even on a language like English, where OCRs have been fairly …

Abstract

Human pose as a query modality is an alternative and rich experience for image and video retrieval. We present a novel approach for the task of human pose retrieval, and make the following contributions: first, we introduce `deep poselets' for pose-sensitive detection of various body parts, that are built on convolutional neural network (CNN) features. These deep poselets significantly outperform previous instantiations of Berkeley poselets [2]. Second, using these detector responses, we construct a pose representation that is suitable for pose search, and show that pose retrieval performance exceeds previous methods by a factor of two. The compared methods include Bag of visual words [24], Berkeley poselets [2] and Human pose estimation algorithms [28]. All the methods are quantitatively evaluated on a large dataset of images built from a number of standard benchmarks together with frames from Hollywood …

Abstract

The problem of labeling the edges present in a single color image as convex, concave, and occluding entities is one of the fundamental problems in computer vision. It has been shown that this information can contribute to segmentation, reconstruction and recognition problems. Recently, it has been shown that this classification is not straightforward even using RGBD data. This makes us wonder whether this apparent simple cue has more information than a depth map? In this paper, we propose a novel algorithm using random forest for classifying edges into convex, concave and occluding entities. We release a data set with more than 500 RGBD images with pixel-wise ground labels. Our method produces promising results and achieves an F-score of 0.84 on the data set.

Abstract

The recognition of human activities is one of the key problems in video understanding. Action recognition is challenging even for specific categories of videos, such as sports, that contain only a small set of actions. Interestingly, sports videos are accompanied by detailed commentaries available online, which could be used to perform action annotation in a weakly-supervised setting. For the specific case of Cricket videos, we address the challenge of temporal segmentation and annotation of actions with semantic descriptions. Our solution consists of two stages. In the first stage, the video is segmented into "scenes", by utilizing the scene category information extracted from text-commentary. The second stage consists of classifying videoshots as well as the phrases in the textual description into various categories. The relevant phrases are then suitably mapped to the video-shots. The novel aspect of this work is the …