In this paper we present a technique to classify five common classes of shapes acquired with a capacitive touch display: finger, ear, cheek, hand hold, half ear-half cheek. The need of algorithms able to discriminate among the aforementioned shapes comes from the growing diffusion of touch screen based consumer devices (e.g. smartphones, tablet, etc.). In this context, detection and the recognition of fingers are fundamental tasks in many touch based user applications (e.g., mobile games). Shape recognition algorithms are also extremely useful to identify accidental touches in order to avoid involuntary activation of the device functionalities (e.g., accidental calls). Our solution makes use of simple descriptors designed to capture discriminative information of the considered classes of shapes. The recognition is performed through a decision tree based approach whose parameters are learned on a set of labeled samples. Experimental results demonstrate that the proposed solution achieves good recognition accuracy.
The high level context image analysis regards many fields as face recognition, smile detection, automatic red eye removal,
iris recognition, fingerprint verification, etc. Techniques involved in these fields need to be supported by more powerful
and accurate routines. The aim of the proposed algorithm is to detect elliptical shapes from digital input images. It can
be successfully applied in topics as signal detection or red eye removal, where the elliptical shape degree assessment can
improve performances. The method has been designed to handle low resolution and partial occlusions. The algorithm is
based on the signature contour analysis and exploits some geometrical properties of elliptical points. The proposed method
is structured in two parts: firstly, the best ellipse which approximates the object shape is estimated; then, through the
analysis and the comparison between the reference ellipse signature and the object signature, the algorithm establishes if
the object is elliptical or not. The first part is based on symmetrical properties of the points belonging to the ellipse, while
the second part is based on the signature operator which is a functional representation of a contour. A set of real images
has been tested and results point out the effectiveness of the algorithm in terms of accuracy and in terms of execution time.
This paper proposes a projective image registration algorithm, oriented to consumer devices. It exploits a “multi-resolution feature based method” for estimating the projective parameters through a 2D Daubechies Discrete Wavelet Transform (DWT). The algorithm has been fully tested with real image sequences acquired by CMOS sensors and compared to other registration techniques. The obtained results highlight the accuracy of the registration parameters.
An objective image quality metric can be used to compare the output of different image processing algorithms, but objective measures are not always well correlated with subjective image quality assessment; the latter implies the use of human observers, thus objective methods able to emulate the Human Visual System (HVS) better than the classical measures are preferred. In this paper a full reference objective metric, based on perceptual criteria and oriented to demosaiced images is proposed.
The basic idea is to model the main artifacts produced by the interpolation process, taking into account the HVS sensibility to the typical aliasing and the zipper defects. The proposed technique has been compared to the DE94 CIELAB metric. Furthermore, two subjective tests have been performed; one relative to the color aliasing artifact and one to the zipper effect. The experimental results highlight that the quality scores obtained by the proposed measures have a similar trend to the DE94 CIELAB metric. Moreover, subjective tests are in accordance with the obtained results.
This technique is useful to evaluate the quality of the interpolation techniques implemented in the image processing pipeline of different digital still cameras.
A new technique able to improve the performance of the standard DCT compression algorithm in terms of compression size, maintaining almost constant the perceived quality is presented. The measured improvement is obtained profiling the relative DCT error inside typical image pipeline of data acquired by digital sensors. Experimental results show the effectiveness of the methodology proposed, validated also by using two perceptual quality metrics.