Computer vision systems are frequently used for inspection and classification of products during manufacturing. Image processing and analysis allows non-invasive extraction of object features within an image and the classification of objects based on the extracted data. Shape, texture and color are typical features that can be extracted from an image and used for object recognition. In this paper, a method of detection, segmentation and classification of resistors captured in digital image, based on their nominal values, is presented. The process consists of the following steps: image segmentation, morphological image processing, representation and description of objects, object features extraction, classification of extracted data using support vector machines (SVM). Experimental results show that the proposed method exhibits solid performance and real-time operating capabilities.

Digital image processing techniques are commonly employed for food classification in an industrial environment. In this paper, we propose the use of supervised learning methods, namely multi-class support vector machines and artificial neural networks to perform classification of different type of almonds. In the process of defining the feature vectors, the proposed method has relied on the principal component analysis to identify the most significant shape and color parameters. The comparative analysis of considered classification algorithms has shown that the higher levels of accuracy in almond classification are attained when support vector machine are used as the basis for classification, rather than artificial neural networks. Moreover, the experimental results have demonstrated that the proposed method exhibits significant levels of robustness and computational efficiency to facilitate the use in the real-time applications. In addition, for the purpose of this paper, a dataset of almond images containing various classes of almonds is formed and made freely available to be used by other researchers in this field.

Individuality of handwriting is the reason why it is used as a common base element for detecting character traits of the writer. It is believed that dynamic information improve the accuracy of the analysis, but they are not contained in an offline handwritten text. In order to recover dynamic information, a novel approach for handwriting trajectory recovery is proposed in this paper. The procedure is based on computing the objective function, which depends on parameters such as the angle of movement, path length, air pen tip movements, etc. The analysis is performed in MATLAB program package, using the text samples from IAM-OnDB database. The experimental results indicate that the average effectiveness of the proposed algorithm is above 75%.

This paper presents the work in progress on the design and testing of a distributed ultrasound-based sensory system for hybrid 1D and 2D environment visualisation. Many common sensors used in robotics, such as infrared and ultrasonic sensors, cameras and lasers mainly focus on quantifying distances and shapes, while rarely have the ability to differentiate among different sensed surfaces/materials. We propose an inexpensive prototype sensory system based on popular ultrasonic sensors which uses ultrasonic reflections to determine the acoustic reflection coefficients. This additional feature allows differentiating among sensed objects. Moreover, the developed ultrasonic cells are equipped with a microcontroller for basic signal processing and a communication link for integration into a sensor network. In this paper, we discuss the possibility of fusing obtained sensor array data and laser measurements.

Objective: This study was aimed to investigate the reliability of a computer application for assessment of the stages of cervical vertebra maturation in order to determine the stage of skeletal maturity. Material and methods: For this study, digital lateral cephalograms of 99 subjects (52 females and 47 males) were examined. The following selection criteria were used during the sample composition: age between 9 and 16 years, absence of anomalies of the vertebrae, good general health, no history of trauma at the cervical region. Subjects with lateral cephalograms of low quality were excluded from the study. For the purpose of this study a computer application Cephalometar HF V1 was developed. This application was used to mark the contours of the second, third and fourth cervical vertebrae on the digital lateral cephalograms, which enabled a computer to determine the stage of cervical vertebral maturation. The assessment of the stages of cervical vertebral maturation was carried out by an experienced orthodontist. The assessment was conducted according to the principles of the method proposed by authors Hassel and Farman. The degree of the agreement between the computer application and the researcher was analyzed using by statistical Cohen Kappa test. Results: The results of this study showed the agreement between the computer assessment and the researcher assessment of the cervical vertebral maturation stages, where the value of the Cohen Kappa coefficient was 0.985. Conclusion: The computer application Cephalometar HF V1 proved to be a reliable method for assessing the stages of cervical vertebral maturation. This program could help the orthodontists to identify the stage of cervical vertebral maturation when planning the orthodontic treatment for the patients with skeletal disharmonies.

Many robotic systems rely on infrared sensors, lasers, cameras and/or ultrasonic transducers for perceiving their environment. Most of these sensors can easily determine the distances to the surrounding objects, and even their shape. However, they are often unable to discriminate among different nearby-placed objects, obstacles, materials or surfaces. This paper presents the design and development of a low-cost ultrasonic-based sensory system, which is able to exploit the information contained in the magnitudes of the reflected sound waves. Therefore, the common ultrasonic distance measurement is complemented with the value of the acoustic reflection coefficient of the observed object. The estimated reflection coefficient facilitates the classification of different materials. Experiments are conducted to demonstrate solid performance of the proposed sensory system.

Different sensors may be used for a robot environment analysis: infrared sensors, laser sensors, sonars, RGB and depth cameras. Most of them provide satisfying information about the distance and the shape of observed objects. However, the main drawback of these sensors is the inability to discriminate among different analyzed objects if the latter share the same color, texture or distance. A distributed ultrasound-based sensory system composed from multiple ultrasonic cells is proposed. The system uses a master-slave control architecture. This paper presents the most important part of such system - a low-cost ultrasonic cell with the ability to classify objects by exploiting the magnitude of reflected ultrasonic waves. Traditional ultrasonic sensors only provide information about the distance, but the presented ultrasonic cell also measures the acoustic reflection coefficient of analyzed object. This coefficient allows to differ among materials or objects. Experiments are conducted to demonstrate the performance of the proposed ultrasonic cell.

Contour-based Fourier descriptors are very simple and effective shape description method used for content-based image retrieval. Similarity between Fourier descriptors is usually computed using measures such as City-block or Euclidean distance. These similarity measures consider all harmonics to be equally important, therefore harmonics with larger magnitude tend to have larger significance during the computation of shape similarity. In order to increase the importance of harmonics with lower magnitude, we propose to use weighted City-block distance for computing shape similarity. The proposed weighting coefficients are inspired by the contrast sensitivity of the human visual system to different spatial frequencies, known as the Contrast Sensitivity Function (CSF). Although weighted distances generally do not improve the retrieval performance, experimental results clearly demonstrate that human observers favour the retrieval system based on the weighted distances, and find it more accurate and relevant.

Contour-based Fourier descriptors are established as a simple and effective shape description method for content-based image retrieval. In order to achieve invariance under rotation and starting point change, most Fourier descriptor implementations disregard the phase of the Fourier coefficients. We introduce a novel method for extracting Fourier descriptors, which preserve the phase of Fourier coefficients and have the desired invariance. We propose specific points, called pseudomirror points, to be used as shape orientation reference. Experimental results indicate that the proposed method significantly outperforms other Fourier descriptor based techniques.

Many robotic systems rely on infrared sensors, lasers, cameras and/or ultrasonic transducers for perceiving their environment. Most of these sensors can easily determine the distances to the surrounding objects, and even their shape. However, they are often unable to discriminate among dif- ferent nearby-placed objects, obstacles, materials or surfaces. This paper presents the design and development of a low-cost ultrasonic-based sensory system, which is able to exploit the information contained in the magnitudes of the reflected sound waves. Therefore, the common ultrasonic distance measurement is complemented with the value of the acoustic reflection coeffi- cient of the observed object. The estimated reflection coefficient facilitates the classification of different materials. Experiments are conducted to demonstrate solid performance of the proposed sensory system. Keywords—Ultrasound; Sensor; Distance; Material; Reflec- tion; Robotics

Shape, color and texture are the most important discriminative elements for content based image retrieval. Fourier descriptors are widely used in shape based image retrieval problems. This paper presents a novel method of extracting Fourier descriptors from the simplest shape signature - complex coordinates. Instead of the commonly used scale normalization with the magnitude of the first harmonic, normalization with the sum of magnitudes of all harmonics is used. This leads to an improved shape scale normalization. All the experimental results indicate that the proposed method outperforms many other state-of-the-art Fourier descriptors based methods, both in terms of retrieval performance and computational time.