Alexandru Drimbarean

Image processing techniques to detect and filter objectionable images based on skin tone and shape recognition

In this paper we describe image-processing techniques to detect and categorize potentially objectionable images based solely on the image content. The techniques include a novel method of matching skin tones based on a fuzzy classification scheme and shape recognition techniques to match faces and other elements of the human anatomy. In particular the color matching technique is significantly more accurate than existing methods documented in literature. These techniques offer a means of filtering images, based solely on graphical content, for a new generation of home Internet appliances.

Low Complexity Global Motion Estimation Techniques for Image Stabilization

Two new global motion estimation methods are proposed. The first one, called sign projection (SP) is obtained by modifying the integral projection estimation method using two thresholds for pixel values. The second method, called binary incrementation (BI), is obtained by using only one threshold for generating binary vectors from two images. It is shown that the proposed approaches provide similar motion estimation accuracy with the integral projection (IP) and phase correlation (PC) methods. Also, they have reduced numerical complexity and memory requirements, leading to shorter processing times as well as lower power consumption. The technique is particularly suitable for implementation in consumer devices such as digital video cameras.

Proof-of-concept and evaluation of a dual function visible/NIR camera for iris authentication in smartphones

As a robust method of person authentication, iris biometrics is making its way in to consumer devices such as smartphones. Current iris image acquisition devices typically work under controlled environment and constrained acquisition conditions. In this paper, the adaption of iris biometrics for unconstrained, hand-held devices such as smartphones is investigated. A prototype device is presented with full system description. This device is equipped with a single image sensor with both visible and NIR sensing capabilities. The device is analysed in terms of its optical properties and iris imaging capabilities. Preliminary results indicate that there are challenges to achieve a reliable recognition performance from the images captured using this device. Current system acquires images with marginal optical quality and spatial resolution in an unconstrained acquisition scenario for iris recognition. Nevertheless, the analyses presented in this paper indicate a similar camera module with improved optics and sensor could combine iris biometrics with conventional front camera functions such as video call and the capture of selfie images.

One scan shadow compensation and visual enhancement of color images

The paper presents a new technique of efficient dynamic range compression and shadow compensation for still color images. The proposed method enhances low light areas while preserving the colors and details, without generating visual artifacts. The approach is based on recursive filtering and contrast stretching techniques, driven by statistical measures of the image and implemented under a logarithmic image processing model. The implementation can be used for any image represented in the RGB or YCbCr color spaces.

Real-Time Video Face Recognition for Embedded Devices

This chapter will address the challenges of real-time video face recognition systems implemented in embedded devices. Topics to be covered include: the importance and challenges of video face recognition in real life scenarios, describing a general architecture of a generic video face recognition system and a working solution suitable for recognizing faces in real-time using low complexity devices. Each component of the system will be described together with the system’s performance on a database of video samples that resembles real life conditions.

A Study of the Influence of the PSF Accuracy on the Quality of Image Deblurring

The paper presents a few recent results obtained in restoration of motion blurred photographs. Qualitative differences between images restored with point spread functions of different shapes, values or sizes are illustrated, using test images and simulated blur.

Adaptive recovery of motion blur point spread function from differently exposed images

Motion due to digital camera movement during the image capture process is a major factor that degrades the quality of images and many methods for camera motion removal have been developed. Central to all techniques is the correct recovery of what is known as the Point Spread Function (PSF). A very popular technique to estimate the PSF relies on using a pair of gyroscopic sensors to measure the hand motion. However, the errors caused either by the loss of the translational component of the movement or due to the lack of precision in gyro-sensors measurements impede the achievement of a good quality restored image. In order to compensate for this, we propose a method that begins with an estimation of the PSF obtained from 2 gyro sensors and uses a pair of under-exposed image together with the blurred image to adaptively improve it. The luminance of the under-exposed image is equalized with that of the blurred image. An initial estimation of the PSF is generated from the output signal of 2 gyro sensors. The PSF coefficients are updated using 2D-Least Mean Square (LMS) algorithms with a coarse-to-fine approach on a grid of points selected from both images. This refined PSF is used to process the blurred image using known deblurring methods. Our results show that the proposed method leads to superior PSF support and coefficient estimation. Also the quality of the restored image is improved compared to 2 gyro only approach or to blind image de-convolution results.

MPEG-7 compliant generalized structure descriptor for still image indexing

This paper proposes a generalized structure descriptor (GSD), that offers an MPEG-7 compliant template for the introduction of a large class of local image content descriptors. The standard MPEG-7 color structure descriptor (CSD) is a particular case of the proposed GSD. The GSD descriptor embed color and spatial distribution information, allowing a compact description of color and texture to be used in content-based image retrieval. We will present several particular cases of spatial image structure description. Experiments show that the proposed descriptors can be successfully used for color texture and general image recognition and retrieval.

Framework for Performance Evaluation and Testing of Image Processing Algorithms

This paper presents an integrated framework developed for performance evaluation and testing of image processing algorithms. The framework consists of two main modules: image database server which handles the storage of images and image testing application which manages the test cases and provides the output results. As a practical example, we show how the framework provides support for evaluation of red eye reduction algorithm from acquiring and storing images, designing the tests and presenting the results.

Computational methods for improving thermal imaging for consumer devices

In consumer imaging, the spatial resolution of thermal microbolometer arrays is limited by the large physical size of the individual detector elements. This also limits the number of pixels per image. If thermal sensors are to find a place in consumer imaging, as the newly released FLIR One would suggest, this resolution issue must be addressed. Our work focuses on improving the output quality of low resolution thermal cameras through computational means. The method we propose utilises sub-pixel shifts and temporal variations in the scene, using information from thermal and visible channels. Results from simulations and lab experiments are presented.