Camera-based OCR scene text detection issues: A review

Camera-based scene text detection and recognition is a research area that has attracted countless attention and had made noticeable progress in the area of deep learning technology, computer vision, and pattern recognition. They are highly recommended for capturing text on-scene images (signboards), documents with a multipart and complex background, images on thick books and documents that are highly fragile. This technology encourages real-time processing since handheld cameras are built with very high processing speed and internal memory, are quite easy and flexible to use than the traditional scanner whose usability is limited as they are not portable in size and cannot be used on images captured by cameras. However, characters captured by traditional scanners pose fewer computational difficulties as compared to camera captured images that are associated with divers’ challenges with consequences of high computational complexity and recognition difficulties. This paper, therefore, reviews the various factors that increase the computational difficulties of Camera-Based OCR, and made some recommendations as per the best practices for Camera-Based OCR systems.

Implementation three-step algorithm based on signed digit number system by using neural network

The need for a simple and effective system that works with high efficiency features such as high processing speed, the ability to solve problems by learning method and accomplish the largest amount of data processing accurately and in little time produces that system, which attracted the efforts of the researcher to employ neural networks in computing away from the complexities that burden traditional computers. We presented a model for the design of the arithmetic circuit for the process of addition the sign digit numbers in a new way to deal with the arithmetic operations, which employment of the use of neural networks, this model includes a theoretical and practical simulation of them. The model relied on the implementation of the addition process based on a three-step algorithm adopted by the signed systems. Which is characterized by the possibility of execution in a parallel way, and therefore it provides the advantage of completion of arithmetic operation regardless of the length of their operands, or in other words, whatever the number of bits in the operands. The simulation of the model is done by entering operands for 6 addition operations (each one has operands are 15-bit length) to be executed simultaneously.

Synthesis and mechanical behavior of composite material reinforced with Guadua fiber and with a polyurethane or polyester matrix

A reactive hot-melt resin (polyurethane) was used to manufacture Guadua composites with a certain flexibility, high processing speed, good initial rigidity, and high temperature performance. These composites can support a moderate tensile stress, allow for large strains at low stresses, and have a low density and a working temperature range of -40 °C and 110 °C. During the flexural test, bamboo composites with reactive polyurethane matrix do not break or fail during the test. A polyurethane-based reactive hot-melt resin was characterized by tensile tests, Shore hardness tests, differential scanning calorimetry, and thermogravimetry. Besides, a composite material was made with Guadua fiber and polyester matrix, which had a greater strength in the test of tension and flexion, although it had a lower percentage of elongation than the composite material with reactive polyurethane. Guadua fiber can increase the strength by 266% of polyurethane matrix and 228% of polyester matrix.

Design and Implementation of Nanotechnology QCA Geometric Greedy Router

This paper presents an optimized geometric greedy router (GGR) based on quantum dot cellular automata (QCA) technology. The proposed structure of GGR is based on a spanning tree of the network. This type of communication does not require an IP address. It uses only local information and can be used in many communication devices. In this paper, we first describe the principal components of the router and then we present their QCA architecture. The QCA technology is the most likely alternative to replace conventional circuits (CMOS) due to their very low power consumption and high processing speed. To consider integration with other complex circuit, we have utilized QCA clock-phase-based technique for the proposed design architecture. The results obtained using the QCA designer tool exhibit the superiority of the presented architecture over the existing designs. The proposed structure shows a reduction of 30% reduction in occupied space. The power dissipation rate of the proposed design is analyzed by QCAPro tool to approve its reliability.

A Machine Learning-Based System for Detecting Leishmaniasis in Microscopic Images

Background: Leishmaniasis, a disease caused by a protozoan, causes numerous deaths in humans each year. After malaria, Leishmaniasis is known to be the deadliest parasitic disease globally. Currently, direct visual detection of Leishmania parasite through microscopy is the “gold standard” for the diagnosis of this disease. However, this method is time-consuming and subject to errors. This study was aimed to develop an artificial intelligence-based algorithm and image processing algorithms for the automatic diagnosis of Leishmaniasis.Methods: The Viola-Jones algorithm was used in this study due to its high recognition speed. This algorithm performs in four stages: detection of Haar-like features, integral image creation, Adaboost training, cascade architecture.Results: A 65% recall and 83% precision was concluded in the detection of macrophages infected with the Leishmania parasite. Also, these numbers were 52% and 35%, respectively, related to amastigotes outside of macrophages.Conclusion: The results contain a fairly high sensitivity, with the specificity being less satisfactory. High processing speed, ease of work, and low expenses are advantages of the presented method compared to other procedures. By adding a few adjustments, this method could be considered a viable option.

Design of Public-Key Algorithms Based on Partial Homomorphic Encryptions

With the rapid development of cloud computing, which has become a key aspect to maintain the security of user information that may be highly confidential and maintained during transport and storage process. The reliance on traditional algorithms that are used to encrypt data are not secure enough because we cannot process the data only after decrypt. In this article is proposed the use of homomorphic encryption to solve this problem because it can deal with encrypted data without the decryption, which can lead to ensuring confidentiality of the data. A number of public-key algorithms are explained, which is based on the concept of homomorphic encryption. In this article an algorithm is proposed based on HE and it is similar to Menesez-EC but with one digit as a secret key according to its advantage, whereby reducing the cost of communication, and storage and provides high processing speed when compared with other algorithms. This algorithm provides enough security for a bank's customer information and then compared with ECC, each of RSA and Piallier algorithms as evaluated.

An Analysis of the Optical System of a Length Measurement Comparator

In the paper, the optical system of a precise bar length measuring comparator is analysed. The requirements for such a system are determined and systematized. The impact of the resolution, signal discretization frequency, image blurring, bar edge measurement indeterminacy and camera noise on measuring the bar width and establishing the bar position is discussed upon. Various algorithms have been analysed and finally a bar edge identification algorithm oriented to the scale calibration accuracy and the high processing speed was proposed. In the end of the paper, conclusions are provided.

Hardware implementation of an α - level based binary search and shifting fuzzifier (α - BSSF)

Fuzzy processors are used for control actions in nonlinear mechatronic systems where high processing speed is required. The Field Programmable Gate Arrays (FPGA) are a good option to implement low cost fuzzy hardware in a short development time. A very important block in fuzzy hardware is the fuzzifier, since it affects directly in the accuracy of the result and in the processing time for obtaining a fuzzy number. There have been many design methodologies intended for enhancing the performance of this block. This paper presents a parallel fuzzifier circuit called α-BSSF. Its main design characteristics are the use of α-levels for membership representation, usage of integer numbers, and avoiding time-consuming operations. As result, we obtained a fuzzifier that shows advantages in the reduction of the response time and computational resources against the existing sequential fuzzification methods. This proposal is targeted not only for T1FS, but also for T2FS, since the membership calculation through fuzzifier is applied in the same way but twice.

MongoDB Database as Storage for GPON Frames

This work is focused on creating an open-source software-based solution for monitoring traffic transmitted through gigabit passive optical network. In this case, the data are captured by the field-programmable gate array (FPGA) card and reassembled using parsing software from a passive optical network built on the International Telecommunication Unit telecommunication section (ITU-T) G.984 gigabit-capable passive optical network GPON recommendation. Then, the captured frames are converted by suitable software into GPON frames, which will be further processed for analysis. Due to the high transfer rate of GPON recommendations, the work describes the issue of writing to the Mongo database system. In order to achieve the best possible results and minimal loss of transmitted frames, a series of tests were performed. The proposed test scenarios are based on different database writing approaches and are implemented in the Python and C# programming languages. Based on our results, it has been shown that the high processing speed is too high for Python processing. Critical operations must be implemented in the C# programming language. Due to rapid application development, Python can only be used for noncritical time-consuming data processing operations.