Facial expression recognition methods use a combination of geometric and appearance-based features. Spatial features are derived from displacements of facial landmarks, and carry geometric information. These features are either selected based on prior knowledge, or dimension-reduced from a large pool. In this study, we produce a large number of potential spatial features using two combinations of facial landmarks. Among these, we search for a descriptive subset of features using sequential forward selection. The chosen feature subset is used to classify facial expressions in the extended Cohn-Kanade dataset (CK+), and delivered 88.7% recognition accuracy without using any appearance-based features.

We present a parallel implementation of the widely-used entropy encoding algorithm, the Huffman coder, on the NVIDIA CUDA architecture. After constructing the Huffman codeword tree serially, we proceed in parallel by generating a byte stream where each byte represents a single bit of the compressed output stream. The final step is then to combine each consecutive 8 bytes into a single byte in parallel to generate the final compressed output bit stream. Experimental results show that we can achieve up to 22× speedups compared to the serial CPU implementation without any constraint on the maximum codeword length or data entropy.

Among various approaches to eye tracking systems, light-reflection based systems with non-imaging sensors, e.g., photodiodes or phototransistors, are known to have relatively low complexity; yet, they provide moderately accurate estimation of the point of gaze. In this paper, a low-computational approach on gaze estimation is proposed using the Eye Touch system, which is a light-reflection based eye tracking system, previously introduced by the authors. Based on the physical implementation of Eye Touch, the sensor measurements are now utilized in low-computational least-squares algorithms to estimate arbitrary gaze directions, unlike the existing light reflection-based systems, including the initial Eye Touch implementation, where only limited predefined regions were distinguished. The system also utilizes an effective pattern classification algorithm to be able to perform left, right, and double clicks based on respective eye winks with significantly high accuracy. In order to avoid accuracy problems for sensitive sensor biasing hardware, a robust custom microcontroller-based data acquisition system is developed. Consequently, the physical size and cost of the overall Eye Touch system are considerably reduced while the power efficiency is improved. The results of the experimental analysis over numerous subjects clearly indicate that the proposed eye tracking system can classify eye winks with 98% accuracy, and attain an accurate gaze direction with an average angular error of about 0.93 °. Due to its lightweight structure, competitive accuracy and low-computational requirements relative to video-based eye tracking systems, the proposed system is a promising human-computer interface for both stationary and mobile eye tracking applications.

Due to the popularity of the prediction concept in time series analysis, predictive coding has been an attractive approach, particularly in lossless image compression. Utilization of prediction in time series not only makes use of residual encoding of the prediction error, but also describes and models the behavior of the underlying process. Unfortunately, this approach seems to have limited most of the scientists in the compression society to focus only to causal (or windowed) predictors, which are fine tuned to particular signal patterns. This work considers the fundamental formulation of finite extent data compression by making use of “adaptive multi-channel” prediction that is constructed by comparing prediction values of separate predictors (called, the multiple predictor cooperation). The deliberately generated channels are observed to have sharp error distributions with different bias centers. These biases are centered in a second pass, to produce plausible experimental predictive compression results.

In this study, we present a new contour-based corner detection method based on the turning angle curvature computed from the contour gradients of the image. In general, curvature is computed with the pixel locations of the extracted image contours. In most contour extraction methods, the image gradient information is already computed. The proposed algorithm makes use of this available information to compute the curvature function and takes local extremums as potential corner candidates. Afterwards, the candidates are validated by a novel validation algorithm which tries to approximate the local geometric structure of the contour with an iterative least squares estimation algorithm. Thus, we not only eliminate the false detected corners; but also estimate the corner strength precisely in terms of degrees. The experiments show that the detected corners with gradient-based turning angle curvature are more durable to affine transformations according to the ACU and LE criterions.

We propose a real-time, parameter-free circle detection algorithm that produces accurate results with very few false positives. The algorithm makes use of the contiguous (connected) set of edge segments produced by our novel edge segment detector, the Edge Drawing (ED) algorithm; hence the name EDCircles. The proposed algorithm first fits line segments to ED's edge segments and then processes these line segments to detect circles in a given image. We show through experimentation that EDCircles works real-time, produces good results, and is very suitable for the next generation real-time automation applications including automatic inspection of manufactured products, human eye iris and pupil detection, circular traffic sign detection, etc.

We present a high-speed contour detector, which we name EDContours, that works by running our real-time parameter-free edge segment detector, Edge Drawing Parameter Free (EDPF), at different scale-space representations of an image. Combining the edge segments detected by EDPF at different scales, EDContours generates a soft contour map for a given image. EDContours works on gray-scale images, is parameter-free, runs very fast, and results in an F-measure score of 0.62 on the Berkeley Segmentation Dataset (BSDS300).

Lane detection algorithms constitute a basis for intelligent vehicle systems such as lane tracking and involuntary lane departure detection. In this paper, we propose a simple and video-based lane detection algorithm that uses a fast vanishing point estimation method. The first step of the algorithm is to extract and validate the line segments from the image with a recently proposed line detection algorithm. In the next step, an angle based elimination of line segments is done according to the perspective characteristics of lane markings. This basic operation removes many line segments that belong to irrelevant details on the scene and greatly reduces the number of features to be processed afterwards. Remaining line segments are extrapolated and superimposed to detect the image location where majority of the linear edge features converge. The location found by this efficient operation is assumed to be the vanishing point. Subsequently, an orientation-based removal is done by eliminating the line segments whose extensions do not intersect the vanishing point. The final step is clustering the remaining line segments such that each cluster represents a lane marking or a boundary of the road (i.e. sidewalks, barriers or shoulders). The properties of the line segments that constitute the clusters are fused to represent each cluster with a single line. The nearest two clusters to the vehicle are chosen as the lines that bound the lane that is being driven on. The proposed algorithm works in an average of 12 milliseconds for each frame with 640×480 resolution on a 2.20 GHz Intel CPU. This performance metric shows that the algorithm can be deployed on minimal hardware and still provide real-time performance.

We propose a real-time, parameter-free edge/edge segment detection algorithm based on our novel edge/edge segment detector, the edge drawing (ED) algorithm; hence the name edge drawing parameter free (EDPF). EDPF works by running ED with ED's parameters set at their extremes. This produces all edge segments in a given image with numerous false detections. The detected edge segments are then validated by an "a contrario" validation step due to the Helmholtz principle, which eliminates invalid detections leaving only "meaningful" edge segments.

We propose a linear time line segment detector that gives accurate results, requires no parameter tuning, and runs up to 11 times faster than the fastest known line segment detection algorithm in the literature; namely, the LSD by Gioi et al. The proposed algorithm also includes a line validation step due to the Helmholtz principle, which lets it control the number of false detections. Our detector makes use of the clean, contiguous (connected) chain of edge pixels produced by our novel edge detector, the Edge Drawing (ED) algorithm; hence the name EDLines. With its accurate results and blazing speed, EDLines will be very suitable for the next generation real-time computer vision applications.

We propose a new edge detection algorithm that works by computing a set of anchor edge points in an image and then linking these anchor points by drawing edges between them. The resulting edge map consists of perfect contiguous, one pixel wide edges. The performance tests show that our algorithm is up to 16% faster than the fastest known edge detection algorithm, i.e., OpenCV implementation of the Canny edge detector. We believe that our edge detector is a novel step in edge detection and would be very suitable for the next generation real-time image processing and computer vision applications.

Enabling peer-to-peer (P2P) communication for hosts behind network address translation (NAT) boxes is an important and difficult problem. Existing proposals, for example, UPnP, MIDCOM, TURN, STUN, STUNT, P2PNAT, NATBlaster among others, offer only partial, limited and non-deterministic solutions. A framework that offers a complete solution to the P2P communication problem is presented. The proposed framework is based on the use of IPv4+4 addresses and the standard IPv4 Loose Source Record Route (LSRR) option and requires no changes whatsoever to end-host protocol stacks and Internet routers. The only requirement is a simple upgrade of border routers with a new LSRR-based packet-forwarding algorithm for the P2P traffic. The implementation of a Linux-based border router that runs the proposed forwarding algorithm is detailed, and how P2P applications can benefit from this framework is described.

In this study, a new eye tracking system, namely Eye Touch, is introduced. Eye Touch is based on an eyeglasses-like apparatus on which IrDA sensitive sensors and IrDA light sources are mounted. Using inexpensive sensors and light sources instead of a camera leads to lower system cost and need for the computation power. A prototype of the proposed system is developed and tested to show its capabilities. Based on the test results obtained, Eye Touch is proved to be a promising human-computer interface system.