Journal Article

Permanent URI for this collectionhttps://ir.daiict.ac.in/handle/123456789/37

Browse

Filters

2005 - 200932010 - 201919

Settings

Author: search.filters.author.Mitra, SumanEnd date: 2019

Search Results

Now showing 1 - 10 of 22
  • Thumbnail Image
    PublicationMetadata only
    Image denoising using orthogonal locality preserving projections
    (SPIE, 01-08-2015) Shikkenawis, Gitam; Mitra, Suman; Rajwade, Ajit; DA-IICT, Gandhinagar; Shikkenawis, Gitam (201221004)
    Image denoising approaches that learn spatially adaptive dictionaries from the observed noisy image have gathered a lot of attention in the past decade. These methods rely on the hypothesis that patches from the underlying clean image can be expressed as sparse linear combinations of these dictionary vectors (bases). We present a framework for inferring an orthonormal set of dictionary vectors using orthogonal locality preserving projection (OLPP). This ensures that patches that are similar in the noisy image should produce similar coefficients when projected in the OLPP domain. Unlike other projection methods, the locality preserving property of OLPP automatically groups similar patches together during inference of the basis. Hence, only one global orthonormal basis suffices to sparsely represent patches from a large subimage or a large portion of the image. The proposed amalgamation of the sparsity and global dictionary make the current approach more suitable for an image denoising task with reduced computational complexity. Experiments on several benchmark datasets made it clear that the proposed method is capable of preserving fine textures while denoising an image, on par with or surpassing several state-of-the-art methods for gray-scale and color images.
  • Thumbnail Image
    PublicationMetadata only
    On reconnection of broken ridges and binarization for fingerprint images
    (01-01-2014) Munshi, Paridhi; Mitra, Suman; DA-IICT, Gandhinagar; MunshI, Paridhi (201011042)
  • Thumbnail Image
    PublicationMetadata only
    Offline handwritten Gujarati numeral recognition using low-level strokes
    (InderScience, 01-10-2015) Goswami, Mukesh M; Mitra, Suman; DA-IICT, Gandhinagar
    This paper focuses on the development of offline handwritten Gujarati numeral database of reasonable size and its recognition using low-level stroke features. The database consists of 14,000 samples collected from 140 people with different age group, educational background, and work culture. A novel technique for the extraction of various low-level stroke features, like endpoints, junction points, line segments, and curve segments, is proposed, and the block-wise histogram of low-level stroke features is used for the recognition of offline handwritten numerals from two of the popular Indian scripts, namely Gujarati and Devanagari. The baseline experiments were performed using k-nearest neighbour (k-NN) classifier, and the results were further improved by using the statistically advance support vector machine (SVM) classifier with radial basis function (RBF) kernel. The average test accuracy obtained on Gujarati and Devanagari database were 98.46% and 98.65%, respectively, which is comparable to other existing work. The experiments were also performed on the mixed numerals recognition from Gujarati-Devanagari and Gujarati-English considering the multi-script scenarios in Indian documents.
  • Thumbnail Image
    PublicationMetadata only
    L1-norm orthogonal neighbourhood preserving projection and its applications
    (Springer, 01-11-2019) Koringa, Purvi A; Mitra, Suman; DA-IICT, Gandhinagar; Koringa, Purvi A (201321010)
    Dimensionality reduction techniques based on manifold learning are becoming very popular for computer vision tasks like image recognition and image classification. Generally, most of these techniques involve optimizing a cost function in L2-norm and thus they are susceptible to outliers. However, recently, due to capability of handling outliers, L1-norm optimization is drawing the attention of researchers. The work documented here is the first attempt towards the same goal where orthogonal neighbourhood preserving projection (ONPP) technique is performed using optimization in terms of L1-norm to handle data having outliers. In particular, the relationship between ONPP and PCA is established theoretically in the light of L2-norm and then ONPP is optimized using an already proposed mechanism of PCA-L1. Extensive experiments are performed on synthetic as well as real data for applications like classification and recognition. It has been observed that when larger number of training data is available L1-ONPP outperforms its counterpart L2-ONPP.
  • Thumbnail Image
    PublicationMetadata only
    Rough set based bilateral filter design for denoising brain MR images
    (Elsevier, 01-08-2015) Phophalia, Ashish; Mitra, Suman; DA-IICT, Gandhinagar; Phophalia, Ashish (201021014)
    A study on bilateral filter for denoising reveals that more informative the filters are, better is the result expected. Moreover, getting precise information of the image with noise is a difficult task. In the current work, a rough set theory (RST) based approach is used to derive pixel level edge map and class labels which in turn are used to improve the performance of bilateral filters. RST handles the uncertainty present in the data even under noise. The basic structure of existing bilateral filter is not changed much, however, boosted up by prior information derived by rough edge map and rough class labels. The filter is extensively applied to denoise brain MR images. The results are compared with that of the state-of-the-art approaches. The experiments have been performed on two real (normal and pathological disordered) human MR databases. The performance of the proposed filter is found to be better, in terms of benchmark metrics.
  • Thumbnail Image
    PublicationMetadata only
    Classification of Printed Gujarati Characters using Low-Level Stroke Features
    (ACM, 12-04-2016) Goswami, Mukesh M; Mitra, Suman; DA-IICT, Gandhinagar
    This article presents an elegant technique for extracting the low-level stroke features, such as endpoints, junction points, line elements, and curve elements, from offline printed text using a template matching approach. The proposed features are used to classify a subset of characters from Gujarati script. The database consists of approximately 16,782 samples of 42 middle-zone symbols from the Gujarati character set collected from three different sources: machine printed books, newspapers, and laser printed documents. The purpose of this division is to add variety in terms of size, font type, style, ink variation, and boundary deformation. The experiments are performed on the database using a k-nearest neighbor (kNN) classifier and results are compared with other widely used structural features, namely Chain Codes (CC), Directional Element Features (DEF), and Histogram of Oriented Gradients (HoG). The results show that the features are quite robust against the variations and give comparable performance with other existing works.
  • Thumbnail Image
    PublicationMetadata only
    ONPPn: Orthogonal Neighborhood Preserving Projection with Normalization and its applications
    (Elsevier, 01-08-2018) Koringa, Purvi A; Mitra, Suman; DA-IICT, Gandhinagar; Koringa, Purvi A (201321010)
    Subspace analysis or�dimensionality reduction techniques�are becoming very popular for many�computer vision tasks�such as image recognition. Most of such techniques deal with optimizing a cost function based on some criteria imposed on either projections of data or on the basis of projection space. NPP and ONPP are such linear methods that preserve local linear relationship within the neighborhood, with two different constraints, normalized projection and�orthogonal basis�of subspace respectively. This article proposes a method, ONPPn, that finds a subspace which satisfies two constraints namely, normalization and�orthogonality. The article also provides two-dimensional variant of ONPPn. Experiments show that ONPPn outperforms its NPP and ONPP versions in image recognition tasks, whereas 2D-ONPPn outperforms 2D-ONPP by huge margin but does not perform as good as 2D-NPP. 2D-NPP as well as 2D-ONPP are not suitable for reconstruction task, but the proposed method 2D-ONPPn overcomes drawbacks of existing methods and is best suited for image reconstruction, too.
  • Thumbnail Image
    PublicationMetadata only
    Shadow-Free, Expeditious and Precise, Moving Object Separation from Video
    (Springer, 25-01-2018) Domadiya, Prashant; Shah, Pratik; Mitra, Suman; DA-IICT, Gandhinagar; Domadiya, Prashant (201521010)
    The foreground�background separation is an essential part of any video-based surveillance system. Gaussian Mixture Models (GMM) based object segmentation method accurately segments the foreground, but it is computationally expensive. In contrast, single Gaussian-based segmentation is computationally inexpensive but inaccurate because it can not handle the variations in the background. There is a trade-off between computation efficiency and precision in the segmentation approach. From the experimental observations, the variations such as lighting variations, shadows, background motion, etc., affect only a few pixels in the frames in temporal direction. So, unaffected pixel can be modeled by single Gaussian in temporal direction while the affected pixels may need GMM to handle the variations in the background. We propose an adaptive algorithm which models pixel dynamically in terms of number of Gaussians in temporal direction. The proposed method is computationally inexpensive and precise. The flexibility in terms of number of Gaussians used to model each pixel, along with�adaptive learning�approach, reduces the time complexity of the algorithm significantly. To resolve spacial occlusion problem, a spatial smoothing is carried out by weighted�Kn�nearest neighbors which improves the overall accuracy of proposed algorithm. To avoid false detection due to illumination variations and shadows in a particular image, illumination invariant representation is used.
  • Thumbnail Image
    PublicationMetadata only
    2D Orthogonal Locality Preserving Projection for Image Denoising
    (IEEE, 15-01-2016) Shikkenawis, Gitam; Mitra, Suman; DA-IICT, Gandhinagar; Shikkenawis, Gitam (201221004)
    Sparse representations using transform-domain techniques are widely used for better interpretation of the raw data. Orthogonal locality preserving projection (OLPP) is a linear technique that tries to preserve local structure of data in the transform domain as well. Vectorized nature of OLPP requires high-dimensional data to be converted to vector format, hence may lose spatial neighborhood information of raw data. On the other hand, processing 2D data directly, not only preserves spatial information, but also improves the computational efficiency considerably. The 2D OLPP is expected to learn the transformation from 2D data itself. This paper derives mathematical foundation for 2D OLPP. The proposed technique is used for image denoising task. Recent state-of-the-art approaches for image denoising work on two major hypotheses, i.e., non-local self-similarity and sparse linear approximations of the data. Locality preserving nature of the proposed approach automatically takes care of self-similarity present in the image while inferring sparse basis. A global basis is adequate for the entire image. The proposed approach outperforms several state-of-the-art image denoising approaches for gray-scale, color, and texture images.
  • Thumbnail Image
    PublicationMetadata only
    On some variants of locality preserving projection
    (Elsevier, 01-01-2016) Shikkenawis, Gitam; Mitra, Suman; DA-IICT, Gandhinagar; Shikkenawis, Gitam (201221004)
    Algorithms strive to capture the intricacies of our complex world, but translating�qualitative�aspects into quantifiable data poses a significant challenge. In our paper, we embark on a journey to unveil the hidden structure of music by exploring the interplay between our predictions and the sequence of musical events. Our ultimate goal is to gain insights into how�certainty�fluctuates throughout a musical piece using a three-fold approach: a listening test, reinforcement learning (RL), and graph construction. Through this approach, we seek to understand how musical expectancy affects physiological measurements, visualize the�graphical structure�of a composition, and analyze the accuracy of�prediction accuracy�across 15 musical pieces. We conducted a listening test using western classical music on 50 subjects, monitoring changes in blood pressure, heart rate, and oxygen saturation in response to different segments of the music. We also assessed the accuracy of the RL agent in predicting notes and pitches individually and simultaneously. Our findings reveal that the average accuracy of the RL agent in note and pitch prediction is 64.17% and 22.48%, respectively, while the accuracy for simultaneous prediction is�73.84%. These results give us a glimpse into the minimum level of certainty present across any composition. To further analyze the accuracy of the RL agent, we propose novel directed graphs in our paper. Our analysis shows that the variance of the edge distributions in the graph is�inversely�proportional to the accuracy of the RL agent. Through this comprehensive study, we hope to shed light on the enigmatic nature of music and pave the way for future research in this fascinating field.