Histogram of oriented gradients

About: Histogram of oriented gradients is a research topic. Over the lifetime, 2037 publications have been published within this topic receiving 55881 citations. The topic is also known as: HOG.

Classification of White Blood Cells using Bispectral Invariant Features of Nuclei Shape

Abstract: Classification of white blood cells from microscope images is a challenging task, especially in the choice of feature representation, considering intra-class variations arising from non-uniform illumination, stage of maturity, scale, rotation and shifting. In this paper, we propose a new feature extraction scheme relying on bispectral invariant features which are robust to these challenges. Bispectral invariant features are extracted from the shape of segmented white blood cell nuclei. Segmentation of white blood cell nuclei is achieved using a level set algorithm via geometric active contours. Binary support vector machines and a classification tree are used for classifying multiple classes of the cells. Performance of the proposed method is evaluated on a combined dataset of 10 classes with 460 white blood cell images collected from 3 datasets and using 5-fold cross validation. It achieves an average classification accuracy of 96.13% and outperforms other popular representations including local binary pattern, histogram of oriented gradients, local directional pattern and speeded up robust features with the same classifier over the same data. The classification accuracy of the proposed method is also compared and benchmarked with the other existing techniques for classification white blood cells into 10 classes over the same datasets and the results show that the proposed method is superior over other approaches.

Image Retrieval using Harris Corners and Histogram of Oriented Gradients

Abstract: based image retrieval is the technique to retrieve similar images from a database that are visually similar to a given query image. It is an active and emerging research field in computer vision. In our proposed system, the Interest points based Histogram of Oriented Gradients (HOG) feature descriptor is used to retrieve the relevant images from the database. The dimensionality of the HOG feature vector is reduced by Principle Component analysis (PCA). To improve the retrieval accuracy of the system the Colour Moments along with HOG feature descriptor are used in this system. The Interest points are detected using the Harris-corner detector in order to extract the image features. The KD-tree is used for matching and indexing the features of the query image with the database images.

Advancing ensemble learning performance through data transformation and classifiers fusion in granular computing context

Abstract: Classification is a special type of machine learning tasks, which is essentially achieved by training a classifier that can be used to classify new instances. In order to train a high performance classifier, it is crucial to extract representative features from raw data, such as text and images. In reality, instances could be highly diverse even if they belong to the same class, which indicates different instances of the same class could represent very different characteristics. For example, in a facial expression recognition task, some instances may be better described by Histogram of Oriented Gradients features, while others may be better presented by Local Binary Patterns features. From this point of view, it is necessary to adopt ensemble learning to train different classifiers on different feature sets and to fuse these classifiers towards more accurate classification of each instance. On the other hand, different algorithms are likely to show different suitability for training classifiers on different feature sets. It shows again the necessity to adopt ensemble learning towards advances in the classification performance. Furthermore, a multi-class classification task would become increasingly more complex when the number of classes is increased, i.e. it would lead to the increased difficulty in terms of discriminating different classes. In this paper, we propose an ensemble learning framework that involves transforming a multi-class classification task into a number of binary classification tasks and fusion of classifiers trained on different feature sets by using different learning algorithms. We report experimental studies on a UCI data set on Sonar and the CK+ data set on facial expression recognition. The results show that our proposed ensemble learning approach leads to considerable advances in classification performance, in comparison with popular learning approaches including decision tree ensembles and deep neural networks. In practice, the proposed approach can be used effectively to build an ensemble of ensembles acting as a group of expert systems, which show the capability to achieve more stable performance of pattern recognition, in comparison with building a single classifier that acts as a single expert system.

Cursive Character Recognition in Natural Scene Images Using a Multilevel Convolutional Neural Network Fusion

Abstract: The accuracy of current natural scene text recognition algorithms is limited by the poor performance of character recognition methods for these images. The complex backgrounds, variations in the writing, text size, orientations, low resolution and multi-language text make recognition of text in natural images a complex and challenging task. Conventional machine learning and deep learning-based methods have been developed that have achieved satisfactory results, but character recognition for cursive text such as Arabic and Urdu scripts in natural images is still an open research problem. The characters in the cursive text are connected and are difficult to segment for recognition. Variations in the shape of a character due to its different positions within a word make the recognition task more challenging than non-cursive text. Optical character recognition (OCR) techniques proposed for Arabic and Urdu scanned documents perform very poorly when applied to character recognition in natural images. In this paper, we propose a multi-scale feature aggregation (MSFA) and a multi-level feature fusion (MLFF) network architecture to recognize isolated Urdu characters in natural images. The network first aggregates multi-scale features of the convolutional layers by up-sampling and addition operations and then combines them with the high-level features. Finally, the outputs of the MSFA and MLFF networks are fused together to create more robust and powerful features. A comprehensive dataset of segmented Urdu characters is developed for the evaluation of the proposed network models. Synthetic text on the patches of images with real natural scene backgrounds is generated to increase the samples of infrequently used characters. The proposed model is evaluated on the Chars74K and ICDAR03 datasets. To validate the proposed model on the new Urdu character image dataset, we compare its performance with the histogram of oriented gradients (HoG) method. The experimental results show that the aggregation of multi-scale and multilevel features and their fusion is more effective, and outperforms other methods on the Urdu character image and Chars74K datasets.

Vision based motorcycle detection using HOG features

Abstract: In this paper, we present a motorcycle detection system in static images leading to its application in crash avoidance systems. Motorcycles are common mode of transport in ASEAN countries and contribute more road crashes than any other mode of transport. In our proposed system, motorbikes are detected based on the helmet and tyre color characteristics. This method involves the fusion of shape, color and corner features to hypothesize motorcycle locations in a video frame. The hypothesized locations are then classified using a support vector machine (SVM) classifier trained on histogram of oriented gradients (HOG) features of motorcycle database. The proposed technique was successfully designed and implemented on a standard PC. It was able to detect single and multiple motorcycles in videos with 96% detection rate.