Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms

Pinto, Diógenes Lodi; Selli, Alana; Tulpan, Dan; Andrietta, Lucas Tassoni; Garbossa, Pollyana Leite Matioli; Voort, Gordon Vander; Munro, Jasper; McMorris, Mike; Alves, Anderson Luís; Carvalheiro, Roberto; Poleti, Mirele Daiana; Balieiro, J. C. C.; Ventura, Ricardo Vieira

doi:10.1016/j.livsci.2022.105152

Cited by 10 publications

(6 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature extraction aims at selecting the most relevant features in problems such as classification and is an important step that involves selection and transformation of raw data into meaningful information ( Pinto et al, 2023 ). An appropriate feature extraction pipeline allows data reduction (in terms of number of variables to be analyzed), in addition to identifying potential crucial features or attributes that are associated with the target variable.…”

Section: Discussionmentioning

confidence: 99%

“…Food quality : in a review regarding sensing technologies used to evaluate carcass composition and quality of meat and fat, Leighton et al (2022) pointed out that CV systems have many applications in this area of expertise, as seen in Pinto et al (2023) , where a model capable of classifying different intramuscular fat patterns in the ribeye area was trained, providing an automatic assessment to meat marbling scoring. Moreover, in order to guarantee milk quality and safety, Lima et al (2022) developed a high performance process to detect milk adulteration with cheese whey through Fourier-transform infrared spectroscopy associated with DL techniques.…”

Section: Applicationsmentioning

confidence: 99%

“…Besides the automation of tasks, AI can contribute by lowering production costs, enhancing productivity, reducing animal stress by minimizing human and animal interaction, and providing data-driven insights for better decision-making ( Rutten et al, 2013 ). It also has the potential to be more precise than humans in certain situations, as this technology can process vast amounts of data quickly and efficiently, allowing the identification of patterns that are not easily detected and reducing the analysis subjectivity ( Pinto et al, 2023 ), which are issues that could significantly affect the success of a project.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: an overview

Curti,

Selli,

Pinto

et al. 2023

Anim. Reprod.

Self Cite

View full text Add to dashboard Cite

Some sectors of animal production and reproduction have shown great technological advances due to the development of research areas such as Precision Livestock Farming (PLF). PLF is an innovative approach that allows animals to be monitored, through the adoption of cutting-edge technologies that continuously collect real-time data by combining the use of sensors with advanced algorithms to provide decision tools for farmers. Artificial Intelligence (AI) is a field that merges computer science and large datasets to create expert systems that are able to generate predictions and classifications similarly to human intelligence. In a simplified manner, Machine Learning (ML) is a branch of AI, and can be considered as a broader field that encompasses Deep Learning (DL, a Neural Network formed by at least three layers), generating a hierarchy of subsets formed by AI, ML and DL, respectively. Both ML and DL provide innovative methods for analyzing data, especially beneficial for large datasets commonly found in livestock-related activities. These approaches enable the extraction of valuable insights to address issues related to behavior, health, reproduction, production, and the environment, facilitating informed decision-making. In order to create the referred technologies, studies generally go through five steps involving data processing: acquisition, transferring, storage, analysis and delivery of results. Although the data collection and analysis steps are usually thoroughly reported by the scientific community, a good execution of each step is essential to achieve good and credible results, which impacts the degree of acceptance of the proposed technologies in real life practical circumstances. In this context, the present work aims to describe an overview of the current implementations of ML/DL in livestock reproduction and production, as well to identify potential challenges and critical points in each of the five steps mentioned, which can affect results and application of AI techniques by farmers in practical situations.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Applicationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: an overview

Curti,

Selli,

Pinto

et al. 2023

Anim. Reprod.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine vision technology involves capturing object images through cameras and converting the visual information into digital data through feature extraction, so as to obtain various features in the source image, and finally understand and make decisions on the detected object according to the discrimination criteria. In the context of livestock and poultry meat, machine vision technology has been proven to be effective in detecting characteristics such as marbling patterns [4], tenderness [5], color [6], and freshness [7]. The common process diagram of a machine vision detection system is illustrated in Figure 1.…”

Section: Machine Vision Technologymentioning

confidence: 99%

Research Progress on Quality Detection of Livestock and Poultry Meat Based on Machine Vision, Hyperspectral and Multi-Source Information Fusion Technologies

Xu,

Han,

Zhao

et al. 2024

Foods

View full text Add to dashboard Cite

Presently, the traditional methods employed for detecting livestock and poultry meat predominantly involve sensory evaluation conducted by humans, chemical index detection, and microbial detection. While these methods demonstrate commendable accuracy in detection, their application becomes more challenging when applied to large-scale production by enterprises. Compared with traditional detection methods, machine vision and hyperspectral technology can realize real-time online detection of large throughput because of their advantages of high efficiency, accuracy, and non-contact measurement, so they have been widely concerned by researchers. Based on this, in order to further enhance the accuracy of online quality detection for livestock and poultry meat, this article presents a comprehensive overview of methods based on machine vision, hyperspectral, and multi-sensor information fusion technologies. This review encompasses an examination of the current research status and the latest advancements in these methodologies while also deliberating on potential future development trends. The ultimate objective is to provide pertinent information and serve as a valuable research resource for the non-destructive online quality detection of livestock and poultry meat.

show abstract

“…Common prediction targets in these cases are the percentage of intramuscular fat and the marbling score. For instance, Pinto et al [12] proposed the application of the local binary pattern method to extract color and texture features, and tree-based machine learning algorithms to classify beef according to their marbling score, and Pannier et al [13] evaluated the capacity of a RGB scanner mounted above a conveyer belt along with a machine learning system to predict intramuscular fat percentage and marbling scores.…”

Section: Introductionmentioning

confidence: 99%

Beef Carcass Grading using Deep Convolutional Networks

Menezes,

Tetila,

Gonçalves

et al. 2023

Anais Do XVIII Workshop De Visão Computacional (WVC 2023)

View full text Add to dashboard Cite

Beef carcass grading is an invaluable tool to ensure meat quality. In most of the Brazilian abattoirs, carcasses are graded through visual analysis by trained graders. In order to automate this process, we evaluate seven image deep learning models. For this purpose, a new dataset was created containing images of 670 bovine half-carcasses taken during regular operation in an abattoir. The images were graded by three professionals. All three experts agreed in only 9.9% of the cases, and two out of three graders agreed in 58.82%. The graders disagreed on 31.28% of the images. These results indicate the complexity of the problem. Nonetheless, an overall accuracy of 53% was achieved using convolutional neural networks, which is close to human performance, when the agreement between the graders is considered. Furthermore, an accuracy of around 91% can be achieved if the cases of disagreement are disregarded.

show abstract

Image feature extraction via local binary patterns for marbling score classification in beef cattle using tree-based algorithms

Cited by 10 publications

References 23 publications

Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: an overview

Applications of livestock monitoring devices and machine learning algorithms in animal production and reproduction: an overview

Research Progress on Quality Detection of Livestock and Poultry Meat Based on Machine Vision, Hyperspectral and Multi-Source Information Fusion Technologies

Beef Carcass Grading using Deep Convolutional Networks

Contact Info

Product

Resources

About