No abstract

We present a longitudinal study of face recognition performance on Children Longitudinal Face (CLF) dataset containing 3, 682 face images of 919 subjects, in the age group [2,18] years. Each subject has at least four face images acquired over a time span of up to six years. Face comparison scores are obtained from (i) a state-of-the-art COTS matcher (COTS-A), (ii) an open-source matcher (FaceNet), and (iii) a simple sum fusion of scores obtained from COTS-A and FaceNet matchers. To improve the performance of the open-source FaceNet matcher for child face recognition, we were able to fine-tune it on an independent training set of 3,294 face images of 1,119 children in the age group [3,18] years. Multilevel statistical models are fit to genuine comparison scores from the CLF dataset to determine the decrease in face recognition accuracy over time. Additionally, we analyze both the verification and open-set identification accuracies in order to evaluate state-of-the-art face recognition technology for tracing and identifying children lost at a young age as victims of child trafficking or abduction.

No abstract

Discontinuity detection plays an important role in image analysis applications like image registration, comparison, segmentation, time sequence analysis and object recognition. This paper presents a new approach for Corner Detection using First Order Difference Chain-Encoding. The proposed method is based on integer operations it is very simple and efficient. Preliminary results are presented and evaluation with respect to standard corner detectors like Harris and Yung is done as a benchmark.

The efficiency of any character recognition technique is directly dependent on the accuracy of the generated feature set that could uniquely represent a character and hence correctly recognize it. This article proposes a hybrid approach combining the structural features of the character and a mathematical model of curve fitting to simulate the best features of a character. As a preprocessing step, skeletonization of the character is performed using an iterative thinning algorithm based on Raster scan of the character image. Then, a combination of structural features of the character like number of endpoints, loops, and intersection points is calculated. Further, the thinned character image is statistically zoned into partitions, and a quadratic curve-fitting model is applied on each partition forming a feature vector of the coefficients of the optimally fitted curve. This vector is combined with the spatial distribution of the foreground pixels for each zone and hence script-independent feature representation. The approach has been evaluated experimentally on Devanagari scripts. The algorithm achieves an average recognition accuracy of 93.4%.