Dissociated Dipoles: Image representation via non-local comparisons

A fundamental question in visual neuroscience is how to represent image structure. The most common representational schemes rely on differential operators that compare adjacent image regions. While well-suited to encoding local relationships, such operators have significant drawbacks. Specifically, each filter's span is confounded with the size of its sub-fields, making it difficult to compare small regions across large distances. We find that such long-distance comparisons are more tolerant to common image transformations than purely local ones, suggesting they may provide a useful vocabulary for image encoding. . We introduce the "Dissociated Dipole," or "Sticks" operator, for encoding non-local image relationships. This operator de-couples filter span from sub-field size, enabling parametric movement between edge and region-based representation modes. We report on the perceptual plausibility of the operator, and the computational advantages of non-local encoding. Our results suggest that non-local encoding may be an effective scheme for representing image structure.

Sparse image representation with encryption

In this thesis we present an overview of sparse approximations of grey level images. The sparse representations are realized by classic, Matching Pursuit (MP) based, greedy selection strategies. One such technique, termed Orthogonal Matching Pursuit (OMP), is shown to be suitable for producing sparse approximations of images, if they are processed in small blocks. When the blocks are enlarged, the proposed Self Projected Matching Pursuit (SPMP) algorithm, successfully renders equivalent results to OMP. A simple coding algorithm is then proposed to store these sparse approximations. This is shown, under certain conditions, to be competitive with JPEG2000 image compression standard. An application termed image folding, which partially secures the approximated images is then proposed. This is extended to produce a self contained folded image, containing all the information required to perform image recovery. Finally a modified OMP selection technique is applied to produce sparse approximations of Red Green Blue (RGB) images. These RGB approximations are then folded with the self contained approach.

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

Evaluation of image resolution and super-resolution on face recognition performance

While researchers strive to improve automatic face recognition performance, the relationship between image resolution and face recognition performance has not received much attention. This relationship is examined systematically and a framework is developed such that results from super-resolution techniques can be compared. Three super-resolution techniques are compared with the Eigenface and Elastic Bunch Graph Matching face recognition engines. Parameter ranges over which these techniques provide better recognition performance than interpolated images is determined.

Supervised latent dirichlet allocation models for efficient activity representation

Local spatio-temporal features with a Bag-of-visual words model is a popular approach used in human action recognition. Bag-of-features methods suffer from several challenges such as extracting appropriate appearance and motion features from videos, converting extracted features appropriate for classification and designing a suitable classification framework. In this paper we address the problem of efficiently representing the extracted features for classification to improve the overall performance. We introduce two generative supervised topic models, maximum entropy discrimination LDA (MedLDA) and class- specific simplex LDA (css-LDA), to encode the raw features suitable for discriminative SVM based classification. Unsupervised LDA models disconnect topic discovery from the classification task, hence yield poor results compared to the baseline Bag-of-words framework. On the other hand supervised LDA techniques learn the topic structure by considering the class labels and improve the recognition accuracy significantly. MedLDA maximizes likelihood and within class margins using max-margin techniques and yields a sparse highly discriminative topic structure; while in css-LDA separate class specific topics are learned instead of common set of topics across the entire dataset. In our representation first topics are learned and then each video is represented as a topic proportion vector, i.e. it can be comparable to a histogram of topics. Finally SVM classification is done on the learned topic proportion vector. We demonstrate the efficiency of the above two representation techniques through the experiments carried out in two popular datasets. Experimental results demonstrate significantly improved performance compared to the baseline Bag-of-features framework which uses kmeans to construct histogram of words from the feature vectors.

Feature Engineering in Fine-Grained Image Classification

Thesis (Ph.D.)--University of Washington, 2013

Representation and learning of visual information for pose recognition

Recovering position from sensor information is an important problem in mobile robotics, known as localisation. Localisation requires a map or some other description of the environment to provide the robot with a context to interpret sensor data. The mobile robot system under discussion is using an artificial neural representation of position. Building a geometrical map of the environment with a single camera and artificial neural networks is difficult. Instead it would be simpler to learn position as a function of the visual input. Usually when learning images, an intermediate representation is employed. An appropriate starting point for biologically plausible image representation is the complex cells of the visual cortex, which have invariance properties that appear useful for localisation. The effectiveness for localisation of two different complex cell models are evaluated. Finally the ability of a simple neural network with single shot learning to recognise these representations and localise a robot is examined.

Colour image coding with matching pursuit in the spatio-frequency domain

We present and evaluate a novel idea for scalable lossy colour image coding with Matching Pursuit (MP) performed in a transform domain. The idea is to exploit correlations in RGB colour space between image subbands after wavelet transformation rather than in the spatial domain. We propose a simple quantisation and coding scheme of colour MP decomposition based on Run Length Encoding (RLE) which can achieve comparable performance to JPEG 2000 even though the latter utilises careful data modelling at the coding stage. Thus, the obtained image representation has the potential to outperform JPEG 2000 with a more sophisticated coding algorithm.

Colour image coding with wavelets and matching pursuit

This thesis considers sparse approximation of still images as the basis of a lossy compression system. The Matching Pursuit (MP) algorithm is presented as a method particularly suited for application in lossy scalable image coding. Its multichannel extension, capable of exploiting inter-channel correlations, is found to be an efficient way to represent colour data in RGB colour space. Known problems with MP, high computational complexity of encoding and dictionary design, are tackled by finding an appropriate partitioning of an image. The idea of performing MP in the spatio-frequency domain after transform such as Discrete Wavelet Transform (DWT) is explored. The main challenge, though, is to encode the image representation obtained after MP into a bit-stream. Novel approaches for encoding the atomic decomposition of a signal and colour amplitudes quantisation are proposed and evaluated. The image codec that has been built is capable of competing with scalable coders such as JPEG 2000 and SPIHT in terms of compression ratio.

RICH AND EFFICIENT VISUAL DATA REPRESENTATION

Increasing the size of training data in many computer vision tasks has shown to be very effective. Using large scale image datasets (e.g. ImageNet) with simple learning techniques (e.g. linear classifiers) one can achieve state-of-the-art performance in object recognition compared to sophisticated learning techniques on smaller image sets. Semantic search on visual data has become very popular. There are billions of images on the internet and the number is increasing every day. Dealing with large scale image sets is intense per se. They take a significant amount of memory that makes it impossible to process the images with complex algorithms on single CPU machines. Finding an efficient image representation can be a key to attack this problem. A representation being efficient is not enough for image understanding. It should be comprehensive and rich in carrying semantic information. In this proposal we develop an approach to computing binary codes that provide a rich and efficient image representation. We demonstrate several tasks in which binary features can be very effective. We show how binary features can speed up large scale image classification. We present learning techniques to learn the binary features from supervised image set (With different types of semantic supervision; class labels, textual descriptions). We propose several problems that are very important in finding and using efficient image representation.

Efficient representation of texture details in medical images by fusion of Ripplet and DDCT transformed images

Purpose: To evaluate and compare the performance of Ripplet Type-1 transform and directional discrete cosine transform (DDCT) and their combinations for improved representation of MRI images while preserving its fine features such as edges along the smooth curves and textures. Methods: In a novel image representation method based on fusion of Ripplet type-1 and conventional/directional DCT transforms, source images were enhanced in terms of visual quality using Ripplet and DDCT and their various combinations. The enhancement achieved was quantified on the basis of peak signal to noise ratio (PSNR), mean square error (MSE), structural content (SC), average difference (AD), maximum difference (MD), normalized cross correlation (NCC), and normalized absolute error (NAE). To determine the attributes of both transforms, these transforms were combined to represent the entire image as well. All the possible combinations were tested to present a complete study of combinations of the transforms and the contrasts were evaluated amongst all the combinations. Results: While using the direct combining method (DDCT) first and then the Ripplet method, a PSNR value of 32.3512 was obtained which is comparatively higher than the PSNR values of the other combinations. This novel designed technique gives PSNR value approximately equal to the PSNR’s of parent techniques. Along with this, it was able to preserve edge information, texture information and various other directional image features. The fusion of DDCT followed by the Ripplet reproduced the best images. Conclusion: The transformation of images using Ripplet followed by DDCT ensures a more efficient method for the representation of images with preservation of its fine details like edges and textures.

The Dystopian Mirror and the Female Body

Women’s experience of the change room mirror is not a particularly affirmative one. The pleasure in looking at the self is dissipated by the ideal feminine ‘I’ that hovers in the shadows of their image of self and others constructing dystopian surveillance and entrapment. This article considers the responses of a number of women bloggers who describe their negative experiences in front of change room mirrors. It also argues that the mirror has been used in positive and creative ways by women artists to assert a self that is not subject to a critical gaze.

Machine recognition of hand-drawn circuit diagrams

An application of image processing techniques to recognition of hand-drawn circuit diagrams is presented. The scanned image of a diagram is pre-processed to remove noise and converted to bilevel. Morphological operations are applied to obtain a clean, connected representation using thinned lines. The diagram comprises of nodes, connections and components. Nodes and components are segmented using appropriate thresholds on a spatially varying object pixel density. Connection paths are traced using a pixel-stack. Nodes are classified using syntactic analysis. Components are classified using a combination of invariant moments, scalar pixel-distribution features, and vector relationships between straight lines in polygonal representations. A node recognition accuracy of 82% and a component recognition accuracy of 86% was achieved on a database comprising 107 nodes and 449 components. This recogniser can be used for layout “beautification” or to generate input code for circuit analysis and simulation packages

A security system based on human iris identification using wavelet transform

A security system based on the recognition of the iris of human eyes using the wavelet transform is presented. The zero-crossings of the wavelet transform are used to extract the unique features obtained from the grey-level profiles of the iris. The recognition process is performed in two stages. The first stage consists of building a one-dimensional representation of the grey-level profiles of the iris, followed by obtaining the wavelet transform zerocrossings of the resulting representation. The second stage is the matching procedure for iris recognition. The proposed approach uses only a few selected intermediate resolution levels for matching, thus making it computationally efficient as well as less sensitive to noise and quantisation errors. A normalisation process is implemented to compensate for size variations due to the possible changes in the camera-to-face distance. The technique has been tested on real images in both noise-free and noisy conditions. The technique is being investigated for real-time implementation, as a stand-alone system, for access control to high-security areas.

Yeondoo Jung

This article analyses Yeondoo Jung's exhibition at MAAP Space, Brisbane. Jung's video artworks works often reveal their mechanisms of pictorial illusion, and expose the apparatuses by which still and moving images are constructed more generally. This article examines the two specific works exhibited at MAAP Space, and situates them in the contexts of moving image theory and practice.