Zohaib Khan

Contour Code: Robust and efficient multispectral palmprint encoding for human recognition

We propose ‘Contour Code’, a novel representation and binary hash table encoding for multispectral palmprint recognition. We first present a reliable technique for the extraction of a region of interest (ROI) from palm images acquired with non-contact sensors. The Contour Code representation is then derived from the Nonsubsampled Contourlet Transform. A uniscale pyramidal filter is convolved with the ROI followed by the application of a directional filter bank. The dominant directional subband establishes the orientation at each pixel and the index corresponding to this subband is encoded in the Contour Code representation. Unlike existing representations which extract orientation features directly from the palm images, the Contour Code uses a two stage filtering to extract robust orientation features. The Contour Code is binarized into an efficient hash table structure that only requires indexing and summation operations for simultaneous one-to-many matching with an embedded score level fusion of multiple bands. We quantitatively evaluate the accuracy of the ROI extraction by comparison with a manually produced ground truth. Multispectral palmprint verification results on the PolyU and CASIA databases show that the Contour Code achieves an EER reduction upto 50%, compared to state-of-the-art methods.

Hyperspectral Imaging for Ink Mismatch Detection

Ink mismatch detection provides important clues to forensic document examiners by identifying whether a particular handwritten note was written with a specific pen, or to show that some part (e.g. signature) of a note is written with a different ink as compared to the rest of the note. In this paper, we show that a hyper spectral image (HSI) of handwritten notes can discriminate between inks that are visually similar in appearance. For this purpose, we develop the first ever hyper spectral image database of handwritten notes in various blue and black inks, comprising a total of 70 hyper spectral images each in 33 bands of the visible spectrum. In an unsupervised clustering scheme, the spectral responses of inks fall into separate clusters to allow segmentation of two different inks in a questioned document. The same method fails to segment inks correctly when applied to RGB scans of these documents, since the inks are very hard to distinguish in the visible spectral range. HSI overcomes the shortcomings of RGB and allows better discrimination between inks. We further evaluate which subset of bands from HSI is most useful for the purpose of ink mismatch detection. We hope that these findings will stimulate the use of HSI in document analysis research, especially for questioned document examination.

Enhancement of exudates for the diagnosis of diabetic retinopathy using Fuzzy Morphology

This paper presents a novel algorithm based on fuzzy morphology for the computer-assisted enhancement of exudates in fundus images of human retina for the diagnosis of diabetic retinopathy. Diabetic retinopathy is a common disease in diabetic persons. The disease is diagnosed by the presence of exudates in the macular region. Here, we use fuzzy morphology for the enhancement of exudates. The fundus image is first converted to grayscale followed by a series of fuzzy erosion and fuzzy dilation (morphological closing operation) with a diamond shaped structuring element. Finally, the resulting image is added to the original image to transform into enhanced one. Experiments were performed on a database of variety of fundus images with and without the disease. The experiments led to convincing results and the images were enhanced for easier clinical examination.

Joint Group Sparse PCA for Compressed Hyperspectral Imaging

A sparse principal component analysis (PCA) seeks a sparse linear combination of input features (variables), so that the derived features still explain most of the variations in the data. A group sparse PCA introduces structural constraints on the features in seeking such a linear combination. Collectively, the derived principal components may still require measuring all the input features. We present a joint group sparse PCA (JGSPCA) algorithm, which forces the basic coefficients corresponding to a group of features to be jointly sparse. Joint sparsity ensures that the complete basis involves only a sparse set of input features, whereas the group sparsity ensures that the structural integrity of the features is maximally preserved. We evaluate the JGSPCA algorithm on the problems of compressed hyperspectral imaging and face recognition. Compressed sensing results show that the proposed method consistently outperforms sparse PCA and group sparse PCA in reconstructing the hyperspectral scenes of natural and man-made objects. The efficacy of the proposed compressed sensing method is further demonstrated in band selection for face recognition.

Automatic ink mismatch detection for forensic document analysis

A key aspect of handwritten document examination is to investigate whether some portion of the text was modified, altered or forged with a different pen. This paper demonstrates the use of hyperspectral imaging for ink mismatch detection in a handwritten note. We propose a novel joint sparse band selection technique that selects informative bands from hyperspectral images for accurate ink mismatch detection. We have developed an end-to-end camera-based hyperspectral document imaging system and collected a database of handwritten notes which has been made publicly available. Algorithmic solutions are presented to handle specific challenges in camera-based hyperspectral document imaging. Extensive experiments show that the proposed band selection method selects the most informative bands and improves average accuracy up to 15%, compared to using all bands. HighlightsInk mismatch detection identifies if part of a note was written with a different ink.Apparently similar inks are automatically distinguished using spectral information.A novel joint sparse band selection method is proposed for ink mismatch detection.A new database is collected using our camera based document imaging system.Extensive experiments are carried out to prove our claims.

Letter to the editor: "The plausibility of arterial-to-venous oxygen shunting in the kidney: it all depends on radial geometry"

to the editor: we read with great interest the recent paper by Olgac and Kurtcuoglu ([5][1]) entitled “Renal oxygenation: pre-glomerular vasculature is an unlikely contributor to renal oxygen shunting.” We commend the authors on their careful approach to the problem of oxygen transport in the

An application of fuzzy morphology for enhancement of aerial images

This paper proposes an approach for structure based separation of image objects using fuzzy morphology for aerial images. With set operators in fuzzy context, we apply an adaptive alpha-cut morphological processing for edge detection and image enhancement. A Top-hat transform is first applied to the input image and the resulting image is thresholded to a binary form. The image is then thinned using hit-or-miss transform. Finally, m-connectivity is used to keep the desired number of connected pixels. The output image is overlaid on the original for enhanced boundaries. Experiments were performed on a variety of aerial images. A comparison to other edge enhancement techniques like Sobel Log and Canny filtering shows improved performance by the proposed technique.

Facial Self Similarity for Sketch to Photo Matching

Automatic recognition of suspects from forensic sketches is of considerable interest to the law enforcement agencies. However, this task is complex due to the heterogenous nature of face sketches and photographs. To address this challenge, previous approaches generally learn a transformation of a sketch to photo or a photo to sketch at the image or feature level in order to reduce the modality gap. Such a transformation may be indeterministic and if learned from training data, is likely to over-fit the sketch artists drawing technique. Instead, we formulate the problem in the context of matching local self similarities which are independently computed from a face sketch and a photo. The proposed Facial Self Similarity (FSS) descriptor is obtained by correlation of a small face patch with its local neighborhood. Thus, our approach avoids the need of a modality transformation, while implicitly reducing the inter-modality gap. The proposed FSS descriptor is evaluated on the CUHK Face Sketch database using sketch-photo pairs of 311 subjects. The FSS descriptor demonstrates high recognition accuracy of 99.53% and outperforms current techniques. We also evaluate the robustness of the descriptor to anomalies such as matching sketches to blurred photographs.

Input devices for virtual surgical simulations: A comparative study

Surgical simulations are becoming the defacto standard for training surgeons for Minimally Invasive Surgery (MIS). Input devices determine how a user will experience the functionality of a simulator. Therefore it is very important to determine which input devices are suitable for the kind of operation that is being performed in a simulator. It is important to perform a user study of these input devices in order to determine their effects on the performance of the software and its usability. In this research we perform a usability study on the different input devices available and study the effect of these input devices on the learning curve of a commercial simulator. We perform our experiments using a mouse, a joystick without force feedback, joystick with force feedback, the PHANTOM Omni device and a custom device designed by our research lab. Using these devices we perform several exercises and study the effect of using these input controls on the learnability of a popular commercial simulator used for training surgeons.

Steganalysis of JPEG Images with Joint Transform Features

In this paper, a universal steganalysis scheme for JPEG images based upon joint transform features is presented. We first analyzed two different transform domains (Discrete Cosine Transform and Discrete Wavelet Transform) separately, to extract features for steganalysis. Then a combination of these two feature sets is constructed and employed for steganalysis. A Fisher Linear Discriminant classifier is trained on features from both clean and steganographic images using all three feature sets and subsequently used for classification. Experiments performed on images embedded with two variants of F5 and Model based steganographic techniques reveal the effectiveness of proposed steganalysis approach by demonstrating improved detection for joint features.