Browsing by Author "Cervantes Jilaja, Claudia"

Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    A New Improvement of Human Bodies Detection
    (Institute of Electrical and Electronics Engineers Inc., 2016) Cervantes Jilaja, Claudia; Tejada Begazo, Maria; Patiño Escarcina, Raquel Esperanza; Barrios Aranibar, Dennis
    The HOG method is applied in the detection of human bodies in an vertical position. However, when human bodies are in other positions, HOG method has several fails, another disadvantage of this method is the occlusion of human bodies by objects. This research presents a new improvement to HOG method with erosion morphological operator and cascade classifier (vector points describing the face of a person). The experiments show that the improved HOG method add erosion operator and classifier of faces (MFHD, Morphological Face HOG Detection) in 79.02% with respect the HOG method whose percentage is 64.46%. © 2015 IEEE.
  • No Thumbnail Available
    Item
    A Semi-Automated Approach for Recognizing Moving Targets Using a Global Vision System
    (Institute of Electrical and Electronics Engineers Inc., 2016) Ripas Mamani, Roger; Cervantes Jilaja, Claudia; Rosas Cuevas, Yessica; Patiño Escarcina, Raquel Esperanza; Barrios Aranibar, Dennis
    Global vision system works with processes of sorting, recognition and identification through some external characteristics as: color, shape and size depending of specific targets. In this paper we propose a semi-automated approach to recognize the targets in moving, where first is performed the image calibration with respect to the lighting and then proceeds to recognize a variety of colors and sizes, through several channels of different color spaces in the processing of video sequences to recognize moving targets, using the proposed algorithm called Color Segmentation (Algorithm 1) to identify a variety of light and dark colors. After semi-automated process is performed the sorting or recognizing of the moving target, where is obtained the position (x, y) of central point and the size of the area (pixels) of the segmentation region. Tests were conducted in: the location of robots in a soccer robot environment (with 94.36% of accuracy) and chestnuts selection process (with 91.80% of accuracy), if the image needs to recognize more than five detections then it proceeds to add parallelism, i.e. add a thread for each segmented color, thus improving processing time. © 2016 IEEE.
  • No Thumbnail Available
    Item
    An Architecture for Computational Control of an Industrial Machine for Classifying Chestnuts
    (Institute of Electrical and Electronics Engineers Inc., 2016) Álvarez Valera, Hernán; Bolivar Vilca, Edwin; Cervantes Jilaja, Claudia; Cuadros Zegarra, Emil; Barrios Aranibar, Dennis; Patiño Escarcina, Raquel Esperanza
    Nowadays, the automation of industrial machines increase the productivity and efficiency of the mass production business. These machines are mainly composed of expensive electrical and mechanical modules to achieve companies production goals. However, many of these do not have information systems capable of providing the user relevant production data. In this work, the authors present an architecture for industrial automation machines of the chestnuts selection process, obtaining some features such as efficiency, effectiveness, high free configurability and low cost of maintenance and construction. This architecture is composed by three different modules: Mechanical components module, responsible of the physical parts management which interact directly with the products. Electrical components module, responsible for transferring data between the computational and mechanical layer through sensors and programs made. Finally, computational layer, responsible for two main tasks: process the necessary selection algorithms, sending the results to the electronic layer and run an information system, used to manage basic machine control operations, and generate the production data through the time. © 2015 IEEE.
  • No Thumbnail Available
    Item
    Automation of Chestnuts Selection Process Using Computer Vision in Real Time
    (IEEE Computer Society, 2016) Alvarez-Valera, Hernan; Bolivar-Vilca, Edwin; Cervantes Jilaja, Claudia; Cuadros Zegarra, Emil; Barrios Aranibar, Dennis; Patiño Escarcina, Raquel Esperanza
    Nowadays, chestnuts selection process in Peru is done by hand, therefore some important problems occur. People who work in this area could make a lot of mistakes because their personal situation or environment variables influence them. Fatigue, feelings, light conditions or working comfort are examples. For this reason the production may become slow and/or imprecise and think about increasing production needs to hire more employees and spend more money. In that sense, it is proposed the automation of the chestnuts selection process for industrial scale, where real time computer vision techniques are applied in order to detect products defects, that are analyzed by some external characteristics: Oval shape to detect the chestnut product and the same descriptor with color and size descriptors to detect the chestnut defects and their types. In this way, this approach allows to improve and increase the quality of the chestnuts selection for its exportation, reducing errors in the process operations. Experimental results show that the performance achieved in each chestnuts selection is 86.78 %. © 2014 IEEE.
  • No Thumbnail Available
    Item
    Morphological Operators Applied to Human Body Detection HOG Method Improvement
    (Institute of Electrical and Electronics Engineers Inc., 2016) Tejada Begazo, Maria; Cervantes Jilaja, Claudia; Patiño Escarcina, Raquel Esperanza; Barrios Aranibar, Dennis
    The HOG method is applied in the detection of human bodies, specially when they are in a vertical position and in many backgrounds. HOG method was evaluated before in different applications such as pedestrian detection, video surveillance, search and rescue. However, when human bodies are in other positions, most of the time, body recognition algorithms present fails. The main idea presented in this research, is the evaluation of different morphological operators applied to improve the HOG method. These experiments show that the results of combining HOG method with morphological operators are better than just using the HOG method. In this research the HOG method combined with morphological operator close (86, 62%) and Erode (84, 35%) had better results than HOG without this pre-processing (77, 32%). © 2015 IEEE.
  • No Thumbnail Available
    Item
    People Detection and Localization in Real Time during Navigation of Autonomous Robots
    (Institute of Electrical and Electronics Engineers Inc., 2016) Lovon Ramos, Percy; Rosas Cuevas, Yessica; Cervantes Jilaja, Claudia; Tejada Begazo, María Fernanda; Patiño Escarcina, Raquel Esperanza; Barrios Aranibar, Dennis
    Currently the navigation involves the interaction of the robot with its environment, this means that the robot has to find the position of obstacles (natural brands and artificial) with respect to its plane. Its environment is time-variant and computer vision can help it to localization and people detection in real time. This article focuses on the detection and localization of people with respect to plane of the robot during the navigation of autonomous robot, for people detection is used Morphological HOG Face Detection algorithm in real-time, where our goal is to localization people in the plane of the robot, obtaining position information relative to the X-Axis (left, right, obstacle) and with the Y-Axis (near, medium, far) with respect robot, to identify the environment in that it's located in the robot is applied the vanishing point detection. Experiments show that people detection and localization is better in the medium region (201 to 600 cm) obtaining 93.13% of accuracy, this allows the robot has enough time to evade the obstacle during navigation, the navigation getting 97.03% of accuracy for the vanishing point detection. © 2016 IEEE.