JCJuan Antonio de Jesús Osuna Coutiño

Juan Antonio de Jesús Osuna Coutiño

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Juan Antonio de Jesús Osuna Coutiño has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Impacto de la biofortificación en Forraje Verde Hidropónico (FVH) basado en fluorescencia

    by Lorena Elizabeth Balandra Aguilar, Madain Pérez Patricio, Ernesto Alonso Ocaña Valenzuela, Juan Antonio de Jesús Osuna Coutiño, Jorge Luis Camas Anzueto, Karina Kristell Aguilar Ovando

    La seguridad alimentaria a nivel global se enfrenta en la actualidad a un fenómeno conocido como “hambre oculta”, el cual consiste en una deficiencia persistente de microntrientes esenciales como el hierro y el zinc en las dietas humanas y animales. Esta problemática afecta la productividad del sector pecuario al reducir la calidad nutricional del forraje. El Forraje Verde Hidropónico (FVH), ha demostrado ser una tecnología de producción intensiva, rápida y eficiente para obtener alimento fresco para ganado en ciclos cortos. Se sugiere la biofortificación del FVH para controlar los micronutrientes al agua de riego para que sean absorbidos por la planta y posteriormente transferidos al consumidor final a través de la cadena alimentaria. Aplicando tecnología como la fluorescencia inducida por láser (LIF), un sistema de visión por computadora y aplicando biofortificantes como el sulfato ferroso, se logra identificar la cantidad de clorofila presente en las hojas y que están relacionados con los niveles de biofortificación en un sistema de producción de FVH.

  • Open Access

    Fuzzy Linear Programming Formulation for Time Prediction in Product Delivery

    by J. A. De Jesús Osuna-Coutiño, Elías Neftalí Escobar Gómez, Alejandro Medina Santiago, Abiel Aguilar-González, Madain Pérez-Patricio, Irvin Hussein Lopez-Nava

    The product delivery process is a set of steps to transport a product of an origin to a delivery point. Nowadays, there are different platforms or software based on classical algorithms for network optimization that help develop routes. Although these informatics systems provide vehicle routes, their prediction time has low accuracy compared to real times in the product distribution, since these systems do not consider the elements that affect route planning, i.e., despite providing vehicle routes, these software systems have low prediction accuracy. To address this problem, an alternative is to use artificial intelligence systems that consider the knowledge of the product delivery planning into route optimization models, thus increasing the time accuracy, but adding the challenge of having to interpret correctly the vehicle route ambiguities. Motivated by the latter, we propose a new fuzzy linear programming formulation to predict delivery times for products. Unlike previous studies, our methodology considers various parameters in the distribution process and offers an effective way to identify which parameters should be used. Our strategy combines the abstraction power of fuzzy logic and the result that provides a route optimization analysis, i.e., this work brings the best of the two worlds to address the difficult problem of shortest-route in product delivery. For that, our methodology has three steps. First, we introduce our formulation that incorporates a Fuzzy Inference System (FIS) into linear programming to achieve accurate time predictions in product delivery. Second, we propose a fuzzy adjustment coefficient to consider the uncertain factors in product distribution and the expertise of the delivery staff. Finally, we develop a Geographic Information System (GIS) to visualize the distribution route and its time. On the other hand, we evaluate this methodology in the routes of a soft drink company using statistical analyses. Experimental results are feasible and promising. For example, in real-world scenarios, our approach reduced the Mean Absolute Percentage Error (MAPE) by 56% compared to methods that utilize artificial intelligence.

  • Open Access

    Learning the Style via Mixed SN-Grams: An Evaluation in Authorship Attribution

    by Juan Pablo Francisco Posadas-Durán, Germán Ríos-Toledo, Erick Velázquez-Lozada, J. A. de Jesús Osuna-Coutiño, Madaín Pérez-Patricio, Fernando Pech May

    This study addresses the problem of authorship attribution with a novel method for modeling writing style using dependency tree subtree parsing. This method exploits the syntactic information of sentences using mixed syntactic n-grams (mixed sn-grams). The method comprises an algorithm to generate mixed sn-grams by integrating words, POS tags, and dependency relation tags. The mixed sn-grams are used as style markers to feed Machine Learning methods such as a SVM. A comparative analysis was performed to evaluate the performance of the proposed mixed sn-grams method against homogeneous sn-grams with the PAN-CLEF 2012 and CCAT50 datasets. Experiments with PAN 2012 showed the potential of mixed sn-grams to model a writing style by outperforming homogeneous sn-grams. On the other hand, experiments with CCAT50 showed that training with mixed sn-grams improves accuracy over homogeneous sn-grams, with the POS-Word category showing the best result. The study’s results suggest that mixed sn-grams constitute effective stylistic markers for building a reliable writing style model, which machine learning algorithms can learn.


  • Open Access

    Three-Dimensional Landing Zone Segmentation in Urbanized Aerial Images from Depth Information Using a Deep Neural Network–Superpixel Approach

    by N. A. Morales-Navarro, J. A. de Jesús Osuna-Coutiño, Madaín Pérez-Patricio, J. L. Camas-Anzueto, J. Renán Velázquez-González, Abiel Aguilar-González, Ernesto Alonso Ocaña-Valenzuela, Juan-Belisario Ibarra-De-La-Garza

    Landing zone detection of autonomous aerial vehicles is crucial for locating suitable landing areas. Currently, landing zone localization predominantly relies on methods that use RGB cameras. These sensors offer the advantage of integration into the majority of autonomous vehicles. However, they lack depth perception, which can lead to the suggestion of non-viable landing zones, as they only assess an area using RGB information. They do not consider if the surface is irregular or accessible for a user (easily accessible to a person on foot). An alternative approach is to utilize 3D information extracted from depth images, but this introduces the challenge of correctly interpreting depth ambiguity. Motivated by the latter, we propose a methodology for 3D landing zone segmentation using a DNN-Superpixel approach. This methodology consists of three steps: First, the proposal involves clustering depth information using superpixels to segment, locate, and delimit zones within the scene. Second, we propose feature extraction from adjacent objects through a bounding box of the analyzed area. Finally, this methodology uses a Deep Neural Network (DNN) to segment a 3D area as landable or non-landable, considering its accessibility. The experimental results are feasible and promising. For example, the landing zone detection achieved an average recall of 0.953, meaning that this approach identified 95.3% of the pixels according to the ground truth. In addition, we have an average precision of 0.949, meaning that this approach segments 94.9% of the landing zones correctly.


  • Open Access

    TurboPixels: A Superpixel Segmentation Algorithm Suitable for Real-Time Embedded Applications

    by Abiel Aguilar-González, Alejandro Medina Santiago, Jorge Antonio Orozco Torres, J. A. de Jesús Osuna-Coutiño, Madaín Pérez Patricio, Néstor A. Morales-Navarro

    Superpixel segmentation aims to produce a consistent grouping of pixels. In recent years, the importance of superpixel segmentation has increased in computer vision since it offers useful primitives for extracting image features and simplifies the complexity of other image processing steps. In this work, we propose the TurboPixels algorithm, whose main contribution is a hardware architecture for superpixel segmentation. Compared with previous approaches, our superpixels are computed without the need for iterative loops. This makes it possible to reduce algorithmic complexity and increases processing speed. The experimental results indicate that our approach enables a small-scale FPGA-based implementation suitable for embedded applications. In addition, the results demonstrate that robust superpixel segmentation can be achieved with processing speeds up to 86 times faster than in previous works in the current literature.


  • Open Access

    Plant Stress Detection Using a Three-Dimensional Analysis from a Single RGB Image

    by Madaín Pérez-Patricio, J. A. de Jesús Osuna-Coutiño, German Ríos-Toledo, Abiel Aguilar-González, J. L. Camas-Anzueto, N. A. Morales-Navarro, J. Renán Velázquez-González, Luis Ángel Cundapí-López

    Plant stress detection involves the process of Identification, Classification, Quantification, and Prediction (ICQP) in crop stress. Numerous approaches exist for plant stress identification; however, a majority rely on expert personnel or invasive techniques. While expert employees demonstrate proficiency across various plants, this approach demands a substantial workforce to ensure the quality of crops. Conversely, invasive techniques entail leaf dismemberment. To overcome these challenges, an alternative is to employ image processing to interpret areas where plant geometry is observable, eliminating the dependency on skilled labor or the need for crop dismemberment. However, this alternative introduces the challenge of accurately interpreting ambiguous image features. Motivated by the latter, we propose a methodology for plant stress detection using 3D reconstruction and deep learning from a single RGB image. For that, our methodology has three steps. First, the plant recognition step provides the segmentation, location, and delimitation of the crop. Second, we propose a leaf detection analysis to classify and locate the boundaries between the different leaves. Finally, we use a Deep Neural Network (DNN) and the 3D reconstruction for plant stress detection. Experimental results are encouraging, showing that our approach has high performance under real-world scenarios. Also, the proposed methodology has 22.86% higher precision, 24.05% higher recall, and 23.45% higher F1-score than the 2D classification method.


  • Open Access

    Supervisory Configuration of Deep Learning Networks for Plant Stress Detection and Synthetic Dataset Generation

    by J. Renán Velázquez-González, Madain Pérez-Patricio, J. A. de Jesús Osuna-Coutiño, Jorge Luis Camas-Anzueto, Abiel Aguilar-González, N. A. Morales-Navarro, Carlos A. Hernández-Gutiérrez

    In computer vision, plant stress detection involves the identification and classification of crop stresses. There are several approaches for the identification of green areas. The most recent approaches rely on machine-learning techniques or deep-learning networks to develop this task. Unfortunately, when attempting to use these networks to detect stressed plants, their performance drastically decreases. In most cases, these networks cannot detect plant stress. In addition, there are extensive repositories of plants on the internet. However, in most cases, these repositories do not include stressed plants. An alternative is to use networks to generate realistic synthetic images; nevertheless, these mathematical models frequently fail to produce accurate synthetic images (increasing supervision and collection times). Motivated by the latter, we propose a supervisory configuration of deep-learning networks to detect stressed plants and generate synthetic databases. This methodology consists of three phases. First, we collected a small set of Internet images of the stressed crops. Second, the process involves final layer training of the image generation model by introducing a new node into the network. Finally, we supervised the generative model using a classification neural network and a feedback loop. This supervision increased the quality of the generated synthetic images. Therefore, the experimental results were promising. The proposed configuration showed a 23.85% increase in average precision and a 10.8% increase in average recall compared with traditional classification architectures using the same synthetic dataset. These results demonstrated the feasibility of this configuration for the classification of stressed crops using synthetic datasets.


  • Open Access

    Object/Scene Recognition Based on a Directional Pixel Voting Descriptor

    by Abiel Aguilar-González, Alejandro Medina Santiago, J. A. de Jesús Osuna-Coutiño

    Detecting objects in images is crucial for several applications, including surveillance, autonomous navigation, augmented reality, and so on. Although AI-based approaches such as Convolutional Neural Networks (CNNs) have proven highly effective in object detection, in scenarios where the objects being recognized are unknow, it is difficult to generalize an AI model for such tasks. In another trend, feature-based approaches like SIFT, SURF, and ORB offer the capability to search any object but have limitations under complex visual variations. In this work, we introduce a novel edge-based object/scene recognition method. We propose that utilizing feature edges, instead of feature points, offers high performance under complex visual variations. Our primary contribution is a directional pixel voting descriptor based on image segments. Experimental results are promising; compared to previous approaches, ours demonstrates superior performance under complex visual variations and high processing speed.

  • Volumetric structure extraction in a single image

    by J. A. de Jesús Osuna-Coutiño, Jose Martinez-Carranza


  • Structure extraction in urbanized aerial images from a single view using a CNN-based approach

    by J. A. de Jesús Osuna-Coutiño, José Martinez-Carranza

    High-Level Structure (HLS) extraction in aerial images consists of recognizing Three-Dimensional (3D) elements on human-made surfaces (objects, buildings, ground, etc.). There are several approaches to HLS extraction in aerial images. However, most of these approaches are based on processing two or more images captured from different camera views or on processing 3D data in the form of point clouds extracted from the camera images. In general, 3D point cloud and multiple view approaches have good performance for certain scenes with video sequences or image sequences, but they need sufficient parallax in order to guarantee accuracy. To address this problem, an alternative is to process a single image seeking to interpret areas of the images where the human-made structure may be observed, thus removing parallax dependency, but adding the challenge of having to interpret image ambiguities correctly. Motivated by the latter, this work presents the results of a novel method for HLS extraction from a single image. Our interest is the buildings structures extraction in urbanized aerial images. For that, our method has six steps. First, we use a new Convolutional Neural Network (CNN) architecture to recognize the labels (tree, roof, and floor) in the input image. Second, we use a CNN to predict the depth. Third, we divide the input image using a superpixel technique. Fourth, we segment the superpixels with its majority label. Fifth, we recognize the structures using a proposed connection analysis that connects the adjacent superpixels with equal labels (tree, roof, and floor). Finally, we use a geometric analysis with the depth prediction of the labels recognized that extracts the 3D shape of the building structure.