Tardi Tjahjadi

Contextual and Variational Contrast Enhancement

This paper proposes an algorithm that enhances the contrast of an input image using interpixel contextual information. The algorithm uses a 2-D histogram of the input image constructed using a mutual relationship between each pixel and its neighboring pixels. A smooth 2-D target histogram is obtained by minimizing the sum of Frobenius norms of the differences from the input histogram and the uniformly distributed histogram. The enhancement is achieved by mapping the diagonal elements of the input histogram to the diagonal elements of the target histogram. Experimental results show that the algorithm produces better or comparable enhanced images than four state-of-the-art algorithms.

Silhouette-based gait recognition using Procrustes shape analysis and elliptic Fourier descriptors

This paper presents a gait recognition method which combines spatio-temporal motion characteristics, statistical and physical parameters (referred to as STM-SPP) of a human subject for its classification by analysing shape of the subjects silhouette contours using Procrustes shape analysis (PSA) and elliptic Fourier descriptors (EFDs). STM-SPP uses spatio-temporal gait characteristics and physical parameters of human body to resolve similar dissimilarity scores between probe and gallery sequences obtained by PSA. A part-based shape analysis using EFDs is also introduced to achieve robustness against carrying conditions. The classification results by PSA and EFDs are combined, resolving tie in ranking using contour matching based on Hu moments. Experimental results show STM-SPP outperforms several silhouette-based gait recognition methods.

Multiscale texture classification using dual-tree complex wavelet transform

This paper presents a multiscale texture classifier that exploits the Gabor-like properties of the dual-tree complex wavelet transform, shift invariance and six directional subbands at each scale, and uses a feature vector comprising of a variance and an entropy at different scales of each of the directional subbands. Experimental results demonstrate its robustness against noise and a higher classification accuracy than a discrete wavelet transform based classifier.

Image texture analysis of sonograms in chronic inflammations of thyroid gland

The current practice in assessing sonographic findings of chronic inflamed thyroid tissue is mainly qualitative, based just on a physicians experience. This study shows that inflamed and healthy tissues can be differentiated by automatic texture analysis of B-mode sonographic images. Feature selection is the most important part of this procedure. We employed two selection schemes for finding recognition-optimal features: one based on compactness and separability and the other based on classification error. The full feature set included Muzzolinis spatial features and Haralicks co-occurrence features. These features were selected on a set of 2430 sonograms of 81 subjects, and the classifier performance was evaluated on a test set of 540 sonograms of 18 independent subjects. A classification success rate of 100% was achieved with as few as one optimal feature among the 129 texture characteristics tested. Both selection schemes agreed on the best features. The results were confirmed on the independent test set. The stability of the results with respect to sonograph setting, thyroid gland segmentation and scanning direction was tested.

A study and modification of the local histogram equalization algorithm

Abstract An analysis of the local histogram equalization algorithm is presented. An adaptation of the algorithm is suggested that involves varying the window size over different regions of the image. This enables each region to be enhanced equally. The algorithm has a parameter, S, to control the amount of stretching required. Some results are presented and analysed.

Adaptive scale fixing for multiscale texture segmentation

This paper addresses two challenging issues in unsupervised multiscale texture segmentation: determining adequate spatial and feature resolutions for different regions of the image, and utilizing information across different scales/resolutions. The center of a homogeneous texture is analyzed using coarse spatial resolution, and its border is detected using fine spatial resolution so as to locate the boundary accurately. The extraction of texture features is achieved via a multiresolution pyramid. The feature values are integrated across scales/resolutions adaptively. The number of textures is determined automatically using the variance ratio criterion. Experimental results on synthetic and real images demonstrate the improvement in performance of the proposed multiscale scheme over single scale approaches.

Robust view-invariant multiscale gait recognition

The paper proposes a two-phase view-invariant multiscale gait recognition method (VI-MGR) which is robust to variation in clothing and presence of a carried item. In phase 1, VI-MGR uses the entropy of the limb region of a gait energy image (GEI) to determine the matching gallery view of the probe using 2-dimensional principal component analysis and Euclidean distance classifier. In phase 2, the probe subject is compared with the matching view of the gallery subjects using multiscale shape analysis. In this phase, VI-MGR applies Gaussian filter to a GEI to generate a multiscale gait image for gradually highlighting the subject?s inner shape characteristics to achieve insensitiveness to boundary shape alterations due to carrying conditions and clothing variation. A weighted random subspace learning based classification is used to exploit the high dimensionality of the feature space for improved identification by avoiding overlearning. Experimental analyses on public datasets demonstrate the efficacy of VI-MGR. HighlightsThe paper proposes a two-phase view-invariant multiscale gait recognition method (VI-MGR).VI-MGR is also robust to clothing variation and presence of a carried item.Phase 1 determines the matching gallery view of the probe using entropy.Phase 2 performs multiscale shape analysis using the Gaussian filter.A subject is classified using weighted random subspace learning to avoid overfitting.

Gait recognition based on shape and motion analysis of silhouette contours

This paper presents a three-phase gait recognition method that analyses the spatio-temporal shape and dynamic motion (STS-DM) characteristics of a human subjects silhouettes to identify the subject in the presence of most of the challenging factors that affect existing gait recognition systems. In phase 1, phase-weighted magnitude spectra of the Fourier descriptor of the silhouette contours at ten phases of a gait period are used to analyse the spatio-temporal changes of the subjects shape. A component-based Fourier descriptor based on anatomical studies of human body is used to achieve robustness against shape variations caused by all common types of small carrying conditions with folded hands, at the subjects back and in upright position. In phase 2, a full-body shape and motion analysis is performed by fitting ellipses to contour segments of ten phases of a gait period and using a histogram matching with Bhattacharyya distance of parameters of the ellipses as dissimilarity scores. In phase 3, dynamic time warping is used to analyse the angular rotation pattern of the subjects leading knee with a consideration of arm-swing over a gait period to achieve identification that is invariant to walking speed, limited clothing variations, hair style changes and shadows under feet. The match scores generated in the three phases are fused using weight-based score-level fusion for robust identification in the presence of missing and distorted frames, and occlusion in the scene. Experimental analyses on various publicly available data sets show that STS-DM outperforms several state-of-the-art gait recognition methods.

Coarse-to-fine planar object identification using invariant curve features and B-spline modeling

Abstract This paper presents a hybrid algorithm for coarse-to-fine matching of affine-invariant object features and B-spline object curves, and simultaneous estimation of transformation parameters. For coarse-matching, two dissimilar measures are exploited by using the significant corners of object boundaries to remove candidate objects with large dissimilarity to a target object. For fine-matching, a robust point interpolation approach and a simple gradient-based algorithm are applied to B-spline object curves under MMSE criterion. The combination of coarse and fine-matching steps reduces the computational cost without degrading the matching accuracy. The proposed algorithm is evaluated using affine transformed objects.

Image Resolution Enhancement Using Dual-Tree Complex Wavelet Transform

In this letter, a complex wavelet-domain image resolution enhancement algorithm based on the estimation of wavelet coefficients is proposed. The method uses a forward and inverse dual-tree complex wavelet transform (DT-CWT) to construct a high-resolution (HR) image from the given low-resolution (LR) image. The HR image is reconstructed from the LR image, together with a set of wavelet coefficients, using the inverse DT-CWT. The set of wavelet coefficients is estimated from the DT-CWT decomposition of the rough estimation of the HR image. Results are presented and discussed on very HR QuickBird data, through comparisons between state-of-the-art resolution enhancement methods.