Intelligent Recognition System Research Articles

Intelligent Identification System Research

From the last two decades years, the human intelligence identification technology has made great progress, and realized from the laboratory to the market, a huge change. Some experts believe that, from the perspective of the development in the future, with the rapid economic and social development, intelligent recognition technology in the future will be gaining popularity and the use of, for example, in the industrial, household appliances industry, communications industry, the automotive industry, household service industry, medical industry and consumer electronic products and many other areas. Intelligent recognition technology will become the information technology is seen as the most important one of the top ten technology. In the DSP, RFID technology is now developing fast, intelligent recognition system will be re-future technology development, from simple voice recognition commands to complex human and computer language and actions of exchange or 3D face recognition, identification system is gradually changing people's everyday life, and to gain significant competitive advantage in the marketplace.

FCaZm intelligent recognition system for locating areas prone to strong earthquakes in the Andean and Caucasian mountain belts

The fuzzy clustering and zoning method (FCAZm) of systems analysis is suggested for recognizing the areas of the probable generation of the epicenters of significant, strong, and the strongest earthquakes. FCAZm is a modified version of the previous FCAZ algorithmic system, which is advanced by the creation of the blocks of artificial intelligence that develop the system-forming algorithms. FCAZm has been applied for recognizing areas where the epicenters of the strongest (M ≥ 73/4) earthquakes within the Andes mountain belt in the South America and significant earthquakes (M ≥ 5) in the Caucasus can emerge. The reliability of the obtained results was assessed by the seismic-history type control experiments. The recognized highly seismic zones were compared with the ones previously recognized by the EPA method and by the initial version of the FCAZ system. The modified FCAZm system enabled us to pass from simple pattern recognition in the problem of recognizing the locations of the probable emergence of strong earthquakes to systems analysis. In particular, using FCAZm we managed to uniquely recognize a subsystem of highly seismically active zones from the nonempty complement using the exact boundary.

Pattern Recognition: Invariance Learning in Convolutional Auto Encoder Network

The ability of the human visual processing system to accommodate and retain clear understanding or identification of patterns irrespective of their orientations is quite remarkable. Conversely, pattern invariance, a common problem in intelligent recognition systems is not one that can be overemphasized; obviously, one’s definition of an intelligent system broadens considering the large variability with which the same patterns can occur. This research investigates and reviews the performance of convolutional networks, and its variant, convolutional auto encoder networks when tasked with recognition problems considering invariances such as translation, rotation, and scale. While, various patterns can be used to validate this query, handwritten Yoruba vowel characters have been used in this research. Databases of images containing patterns with constraints of interest are collected, processed, and used to train and simulate the designed networks. We provide extensive architectural and learning paradigms review of the considered networks, in view of how built-in invariance is learned. Lastly, we provide a comparative analysis of achieved error rates against back propagation neural networks, denoising auto encoder, stacked denoising auto encoder, and deep belief network.

Design of intelligent recognition system based on gait recognition technology in smart transportation

With the rapid development of urban smart transportation, automatic fare collection system becomes more and more important. The related device based on recognition system in the smart transportation is a key equipment of automatic fare ticket system. It is part of the automatic fare collection system and passenger interface. Because of the complexity of the passenger traffic, how the intelligent recognition system can identify the passengers is a formidable challenge. In this paper, we design a sort of intelligent recognition system based on the simplified human gait recognition algorithm. Firstly, we analyze and study the existing identification system. After that we propose the improved and optimized algorithm and design layout of the sensors. And then, according to the motion including action, event and behavior, we propose a simplified method using infrared sensor based on XYT human gait recognition model. This system can effectively reduce the recognition system's judgment and computation time, and improve the accuracy of judgment. Therefore, the proposed system has a certain application value.

Leaves Recognition System Using a Neural Network

Leaf recognition has been gained an importance since the increment of intelligent applications in different platforms such as desktop and mobile. Each leaf contains unique distinct pattern on it that provides effective input for neural networks in order to recognize the type of the leaf correctly. In this paper, intelligent recognition system is presented to recognize and identify 27 different types of leaves using back propagation neural network and results show that the developed system is superior to recent researches with the recognition rate of 97.2%.

A hybrid intelligent recognition system for the early detection of strokes

The increasing prevalence of wearable sensors and low-cost mobile devices have prompted the development of systems for automated diagnosis. Here we focus on models and algorithms for the early detection of strokes that are implanted in a wearable dev

Adaptive Optimal Kernel Time–Frequency Representation Technique for Partial Discharge Ultra-high-frequency Signals Classification

An intelligent system for automatic partial discharge pattern recognition is proposed using adaptive optimal kernel time-frequency representation and a fuzzy k-nearest neighbor classifier. The adaptive optimal kernel technique is employed to acquire the joint time-frequency information for partial discharge signals, which is characterized by the adaptive optimal kernel amplitude matrix. A new feature extraction algorithm, i.e., non-negative matrix factorization aided principal component analysis, is proposed to solve the difficulties of principal component analysis for feature extraction of partial discharge adaptive optimal kernel amplitude matrices due to the high dimensionality. Using an ultra-high frequency detector, 600 partial discharge signals sampled from 4 categories of typical artificial defect models in the laboratory are employed for testing. It is shown that the maximum classification accuracy of 94.33% is obtained considering different non-negative matrix factorization parameter r and various non-negative matrix factorization iterations T. Also, the classification performance of the non-negative matrix factorization–principal component analysis features is superior to that of principal component analysis features extracted from original partial discharge signals, two-dimensional non-negative matrix factorization features and phase-resolved partial discharge statistical operators. The proposed technique can be used for partial discharge pattern recognition based on ultra-high-frequency detection arrangements.

Intelligent System for Diagnosis of Erythema Migrans

Lyme borreliosis is the most common human tick-borne infectious disease of the Northern Hemisphere. One of the first signs of the disease is erythema migrans, a skin lesion that appears within days to weeks after an infected tick bite. In this article, a novel intelligent system for erythema migrans recognition is presented based on image and text information, applicable for individual and clinical web-based use. Novelties of our approach include a combination of visual and textual attributes, a new combination of visual attributes (geometrical, color, and Gabor-filter based), and a new algorithm for calculation of color-based attributes. Procedurally, the intelligent system for erythema migrans recognition integrated in a web-based application facilitates provisional diagnosis of erythema migrans in the general population and assists general medical practitioners in their decisions. Several classification methods—Naïve Bayes, Support Vector Machine, Adaboost, and Random forest—were tested in order to achieve improved performance.

The Design of the Intelligent Voice Recognition System Based on Labview

The recognition of speech sounds test system based on virtual instrument was designed successfully. For years, virtual instrument has become a huge active communication platform for user, and covered the multiple industries and fields of applications, becoming the data acquisition and instrument control the best choice. Based on the Labview 8.5 software platform, combined with PC sound card, microphones and other hardware acquisition of speech signal, the speech signal is filtered. Through the Hamming window, and power spectrum, the recognition of speech signal is realized. After the actual test and application, software operation is stable and reliable, with certain practicability and value of popularization and application.

A VidEo-Based Intelligent Recognition and Decision System for the Phacoemulsification Cataract Surgery.

The phacoemulsification surgery is one of the most advanced surgeries to treat cataract. However, the conventional surgeries are always with low automatic level of operation and over reliance on the ability of surgeons. Alternatively, one imaginative scene is to use video processing and pattern recognition technologies to automatically detect the cataract grade and intelligently control the release of the ultrasonic energy while operating. Unlike cataract grading in the diagnosis system with static images, complicated background, unexpected noise, and varied information are always introduced in dynamic videos of the surgery. Here we develop a Video-Based Intelligent Recognitionand Decision (VeBIRD) system, which breaks new ground by providing a generic framework for automatically tracking the operation process and classifying the cataract grade in microscope videos of the phacoemulsification cataract surgery. VeBIRD comprises a robust eye (iris) detector with randomized Hough transform to precisely locate the eye in the noise background, an effective probe tracker with Tracking-Learning-Detection to thereafter track the operation probe in the dynamic process, and an intelligent decider with discriminative learning to finally recognize the cataract grade in the complicated video. Experiments with a variety of real microscope videos of phacoemulsification verify VeBIRD's effectiveness.

The Research of Event Detection and Characterization Technology of Ticket Gate in the Urban Rapid Rail Transit

Making events recognition more reliable under complex environment is one of the most important challenges for the intelligent recognition system to the ticket gate in the urban rapid rail transit. The motion objects passing through the ticket gate could be described as a series of moving sequences got by sensors that located in the walkway side of the ticket gate. This paper presents a robust method to detect some classes of events of ticket gate in the urban rapid rail transit. Diffused reflectance infrared sensors are used to collect signals. In this paper, the motion objects are here referred to passenger(s) or (and) luggage(s), for which are of frequent occurrences in the ticket gate of the urban railway traffic. Specifically, this paper makes two main contributions: 1) The proposed recognition method could be used to identify several events, including the event of one person passing through the ticket gate, the event of two consecutive passengers passing through the ticket gate without a big gap between them, and the event of a passenger walking through the ticket gate pulling a suitcase; 2) The moving time sequence matrix is transformed into a one-dimensional vector as the feature descriptor. Deep learning (DL), back propagation neural network (BP), and support vector machine (SVM) are applied to recognize the events respectively. BP has been proved to have a higher recognition rate compared to other methods. In order to implement the three algorithms, a data set is built which includes 150 samples of all kinds of events from the practical tests. Experiments show the effectiveness of the proposed methods.

Hybrid intelligent system-based rough set and ensemble classifier for breast cancer diagnosis

The effectiveness of classification and recognition systems has improved in a great deal to help medical experts in diagnosing diseases. Breast cancer is becoming a leading cause of death among women in the whole world; meanwhile, it is confirmed that the early detection and accurate diagnosis of this disease can ensure a long survival of the patients. This paper presents a hybrid intelligent system for recognition of breast cancer tumors. The proposed system includes two main modules: the feature extraction module and the predictor module. In the feature extraction module, rough set theory is used to preprocess the attributes on condition that the important information is not lost, deletes redundant attributes and conflicting objects from decision table. In the predictor module, a combined classifier is proposed based on K-nearest neighbor classifier. Experiments have been conducted on a widely used Wisconsin breast cancer dataset taken from University of California Irvine. Experimental results show that the proposed hybrid system can improve the rate of correct diagnosis of cases. The proposed combined classifier with rough set-based feature selection achieves 99.41 % classification accuracy and uses only 4 features which is the best shown to date. Different performance metrics are used to show the effectiveness of the proposed hybrid system. With these results, the proposed method is very promising compared to the previously reported results and can be used confidently for other breast cancer diagnosis problems.

Automatic recognizing of vocal fold disorders from glottis images.

The laryngeal video stroboscope is an important instrument to test glottal diseases and read vocal fold images and voice quality for physician clinical diagnosis. This study is aimed to develop a medical system with functionality of automatic intelligent recognition of dynamic images. The static images of glottis opening to the largest extent and closing to the smallest extent were screened automatically using color space transformation and image preprocessing. The glottal area was also quantized. As the tongue base movements affected the position of laryngoscope and saliva would result in unclear images, this study used the gray scale adaptive entropy value to set the threshold in order to establish an elimination system. The proposed system can improve the effect of automatically captured images of glottis and achieve an accuracy rate of 96%. In addition, the glottal area and area segmentation threshold were calculated effectively. The glottis area segmentation was corrected, and the glottal area waveform pattern was drawn automatically to assist in vocal fold diagnosis. When developing the intelligent recognition system for vocal fold disorders, this study analyzed the characteristic values of four vocal fold patterns, namely, normal vocal fold, vocal fold paralysis, vocal fold polyp, and vocal fold cyst. It also used the support vector machine classifier to identify vocal fold disorders and achieved an identification accuracy rate of 98.75%. The results can serve as a very valuable reference for diagnosis.

A PWM-Mode Pixel-Parallel Image-Processing Circuit Performing Directional State-Propagation and Its Application to Subjective Contour Generation

As an approach to constructing highly organized and intelligent image recognition systems mimicking the visual architecture in the human brain, we have designed an image processing circuit that performs a directional pixel-state propagation algorithm based on a pixel-parallel architecture using pulse-width modulation (PWM) signals. Directional pixel-state propagation can be used for subjective contour generation, which is a typical function of the visual system in the human brain to fill gaps in natural-image information. A PWM-mode circuit can provide more compact circuit configuration than digital circuits, and can achieve focal-plane analog processing by combining with image sensors without A/D converters. Such circuits are suitable for repetitive algorithms, which require offset-free arithmetic. The proof-of-concept LSI chip has been designed and fabricated using a 0.25 $$\upmu $$μm mixed-signal CMOS process. There are 35 $$\times $$A— 35 processing units included in the chip, the operation cycle time for propagation step is 2.2 $$\upmu $$μs, and the power consumption is 363 mW at a supply voltage of 3.3 V. In experiments using this LSI chip, we have successfully generated subjective contours of Kanizsa figures.

Study of Fingerprint Image Preprocessing Technology

Fingerprint image preprocessing technology has been widely used with the development of intelligent identity recognition system, which studies fingerprint image restoration, enhancement and thinning based on digital image processing technology. This paper presents system design and realization of preprocessing technology for fingerprint image. Fingerprint image has restoration processing by adopting image filed calculation, image background segmentation, image equalization, image convergence and image smoothing algorithm in order at first. Then Gabor wavelet algorithm is used to enhance the contrast of fingerprint image. Image thinning algorithm is carried out to extract the skeleton of fingerprint image at last. Test result shows that the method presented has good accuracy, quick speed and strong robustness for realtime application.

Study of Fingerprint Image Preprocessing Technology

Fingerprint image preprocessing technology has been widely used with the development of intelligent identity recognition system, which studies fingerprint image restoration, enhancement and thinning based on digital image processing technology. This paper presents system design and realization of preprocessing technology for fingerprint image. Fingerprint image has restoration processing by adopting image filed calculation, image background segmentation, image equalization, image convergence and image smoothing algorithm in order at first. Then Gabor wavelet algorithm is used to enhance the contrast of fingerprint image. Image thinning algorithm is carried out to extract the skeleton of fingerprint image at last. Test result shows that the method presented has good accuracy, quick speed and strong robustness for realtime application.

An intelligent system for paper currency recognition with robust features

Intelligent systems on Paper currency recognition and verification are inevitable for modern banking services. These systems are used in Auto-seller machines, vending machines etc. Extracting sufficient and reliable monetary characteristics are essential for accuracy and performance of such systems. This paper proposes a new intelligent system for paper currency recognition. Pakistani paper currency has been considered, as a case study, for intelligent recognition. This paper identifies, introduces, and extracts robust features from Pakistani banknotes. After extracting these features, the paper proposes to use three layers feed-forward Backpropagation Neural Network (BPN) for intelligent classification. The proposed technique and system are simple and comparatively less time consuming which makes it suitable for real-time applications. In order to evaluate the performance of the proposed technique, experiments have been conducted on 175 Pakistani banknotes. The results indicate that system has 100% recognition ability on properly captured images.

A machine learning based intelligent vision system for autonomous object detection and recognition

Existing object recognition techniques often rely on human labeled data conducting to severe limitations to design a fully autonomous machine vision system. In this work, we present an intelligent machine vision system able to learn autonomously individual objects present in real environment. This system relies on salient object detection. In its design, we were inspired by early processing stages of human visual system. In this context we suggest a novel fast algorithm for visually salient object detection, robust to real-world illumination conditions. Then we use it to extract salient objects which can be efficiently used for training the machine learning-based object detection and recognition unit of the proposed system. We provide results of our salient object detection algorithm on MSRA Salient Object Database benchmark comparing its quality with other state-of-the-art approaches. The proposed system has been implemented on a humanoid robot, increasing its autonomy in learning and interaction with humans. We report and discuss the obtained results, validating the proposed concepts.

Study on the Shift Schedule Based on Driver Type of Automatic Mechanical Transmission

An intelligent recognition system of driver type suitable for different drivers was studied in this paper,and the driving style recognition based on BP neural network classifier structure was designed to make different types of shift schedules to adapt to different drivers.The intelligent recognition of driver type was verified by simulation.The rusults showed that the intelligent recognition based on BP neural network classifier structure had good adaptive ability,which could meet the requirements of different types of drivers.

An Improved D-S Evidence Theory Based on Genetic Algorithm to VIP Intelligent Recognition and Recommendation System

In this paper, we use GA to improve the D-S evidence theory, and apply the improved D-S evidence theory to VIP intelligent recognition and recommendation system. In the VIP intelligent recognition and recommendation system of clothes, there are three main evidences: body size, personal preferences, and purchase records. So collision often happens inevitable. This requirement asks us to find out a suitable method to identify the VIPs needs. D-S evidence theory can improve the rate of identification, but has no idea about the collision. The improved D-S evidence theory based on genetic algorithm can deal with the collision evidence and improve the rate of the identification and the stability. As such we can provide VIP more suitable recommendation. The experiment results of clothes recommendation demonstrate the flexibility of the improved method.