Computer-based Vision Systems Research Articles

Development of a harmonized and risk-based code system for post-mortem inspection of broilers

In most European countries, findings detected at post-mortem inspection (PMI) of broilers at slaughter are registered using national or regional code systems. The aim of this study was to map and compare existing national broiler PMI code systems in Europe and to suggest a new harmonized and risk-based code set intended to be interpreted in the same way in all countries. Information about the code systems, condemnation criteria, and the proportion of unfit broiler carcasses in 2022, as well as reasons justifying condemnation, were collected from nine European countries through an online survey. The reasons for declaring meat as unfit for human consumption were divided into food safety, meat quality, broiler health, or broiler welfare. The data were analyzed, and a risk-based code set consisting of 13 codes was developed. Ten of these new codes cover 80% of all condemnations listed in the data retrieved from the countries in the study. The remaining three codes are indicators of broiler welfare. The results were presented in the form of spider diagrams, indicating massive differences between the countries. Harmonization of the code list and the associated decision criteria will allow PMI to be conducted in the same way in different abattoirs and countries. This standardization of the PMI of broilers will enable detailed analysis of PMI results for further use in risk-based meat safety assurance systems and the implementation of computer-based vision systems at PMI in the future.

Current Applications of Artificial Intelligence in Benign Prostatic Hyperplasia.

Artificial intelligence is used in predicting the clinical outcomes before minimally invasive treatments for benign prostatic hyperplasia, to address the insufficient reliability despite multiple assessment parameters, such as flow rates and symptom scores. Various models of artificial intelligence and its contemporary applications in benign prostatic hyperplasia are reviewed and discussed. A search strategy adapted to identify and review the literature on the application of artificial intelligence with a dedicated search string with the following keywords: "Machine Learning," "Artificial Intelligence," AND "Benign Prostate Enlargement" OR "BPH" OR "Benign Prostatic Hyperplasia" was included and categorized. Review articles, editorial comments, and non-urologic studies were excluded. In the present review, 1600 patients were included from 4 studies that used different classifiers such as fuzzy systems, computer-based vision systems, and clinical data mining to study the applications of artificial intelligence in diagnoses and severity prediction and determine clinical factors responsible for treatment response in benign prostatic hyperplasia. The accuracy to correctly diagnose benign prostatic hyperplasia by Fuzzy systems was 90%, while that of computer-based vision system was 96.3%. Data mining achieved sensitivity and specificity of 70% and 50%, respectively, in correctly predicting the clinical response to medical treatment in benign prostatic hyperplasia. Artificial intelligence is gaining attraction in urology, with the potential to improve diagnostics and patient care. The results of artificial intelligence-based applications in benign prostatic hyperplasia are promising but lack generalizability of results. However, in the future, we will see a shift in the clinical paradigm as artificial intelligence applications will find their place in the guidelines and revolutionize the decision-making process.

Current Applications of Artificial Intelligence in Benign Prostatic Hyperplasia.

Artificial intelligence is used in predicting the clinical outcomes before minimally invasive treatments for benign prostatic hyperplasia, to address the insufficient reliability despite multiple assessment parameters, such as flow rates and symptom scores. Various models of artificial intelligence and its contemporary applications in benign prostatic hyperplasia are reviewed and discussed. A search strategy adapted to identify and review the literature on the application of artificial intelligence with a dedicated search string with the following keywords: "Machine Learning," "Artificial Intelligence," AND "Benign Prostate Enlargement" OR "BPH" OR "Benign Prostatic Hyperplasia" was included and categorized. Review articles, editorial comments, and non-urologic studies were excluded. In the present review, 1600 patients were included from 4 studies that used different classifiers such as fuzzy systems, computer-based vision systems, and clinical data mining to study the applications of artificial intelligence in diagnoses and severity prediction and determine clinical factors responsible for treatment response in benign prostatic hyperplasia. The accuracy to correctly diagnose benign prostatic hyperplasia by Fuzzy systems was 90%, while that of computer-based vision system was 96.3%. Data mining achieved sensitivity and specificity of 70% and 50%, respectively, in correctly predicting the clinical response to medical treatment in benign prostatic hyperplasia. Artificial intelligence is gaining attraction in urology, with the potential to improve diagnostics and patient care. The results of artificial intelligence-based applications in benign prostatic hyperplasia are promising but lack generalizability of results. However, in the future, we will see a shift in the clinical paradigm as artificial intelligence applications will find their place in the guidelines and revolutionize the decision-making process.

Simple Vision System for Apple Varieties Classification

Every variety of apple has its particular physical characteristics, which are affected by different pre-harvest factors. Manual classification of these varieties by human labor has several weaknesses, such as the inconsistency, subjectivity, fatigue and different accuracy due to different level of experience of the inspector. This study was aimed to design and evaluate a simple computer-based vision system for recognizing and grading several varieties of apples based on their physical characteristics. Images of apples were taken and were used as training data with different algorithms to extract the particular characteristics of each variety, such as color and shape. The extracted Hue color channels and contour vector were recorded as the reference data and were used to recognize the similar characteristic of those images from the testing data group. The k-nearest neighbors algorithm was used to decide whether an apple belongs to a particular variety. The results show that the recognition rate based on color only was between 84–97% and it was between 5–77% it is based on the shape only. Rotating the image significantly increases the recognition rate (to be between 5 - 69% based on the shape only). Moreover, combining both color and shape characteristics significantly improves the recognition rate.

A practical computer based vision system for posture and movement sensing in occupational medicine

Back pain and upper extremities injuries due to overexertion account for over twenty percent of leave days from work in the US. This explains why a vast amount of initiatives have been, to this date, carried out aiming at reducing the occurrence of such type of injuries. However, although such type of lesions are among the most studied in occupational medicine, no automatic detection and prevention technologies are pervasively available, to this date, at workplaces. Such deficiency is ascribable to the absence of any flexible and cost-effective tectaphnology that may play such role. This work aims at filling such gap: the contribution of this paper is the design and implementation of a movement-posture computer-vision based system that, performing as a sensor, can detect overexertion movements, helping avoid the most common injuries that these cause. Such tasks are carried out with the use of a simple webcam, thus not requiring any expensive or specialized (e.g., Microsoft Kinect) hardware device. The proposed technology is, hence, easily affordable by any type of company and production plant throughout the world and easy adaptable to recognize and detect a wide set of movements and postures. The validity of such approach is demonstrated in realistic settings through a wide set of experiments.

A computer-based vision systems for automatic identification of plant species using kNN and genetic PCA

Precision farming involves integration of different areas of disciplines to lower production costs and improve productivity. One major arm of precision farming or agriculture is the development of computer-based vision systems for automatic identification of plant species. This work involves application of k Nearest Neighbour (kNN) and genetic principal component analysis (GA-PCA) for the development of computer-based vision systems for automatic identification of plant species. As the first contribution, several image descriptors were extracted from the images of plants found in the Flavia dataset. Lots of these image features are affine maps and amalgamation of such massive features in one study is a novel idea. These descriptors are Zernike Moments (ZM), Fourier Descriptors (FDs), Lengendre Moments (LM) Hu 7 Moments, Texture, Geometrical properties and colour features. The GA-PCA (1907 x 41) feature space improved the classification accuracy of kNN from 84.98% to 88.75%.

A survey of computer-based vision systems for automatic identification of plant species

Plants are unavoidable for the existence of most living things on this planet. There are many needs of both humans and animals that are satisfied by materials from plants. These needs include food, shelter, and medicine. The ability to identify plants is highly important in several applications, including conservation of endangered plant species, rehabilitation of lands after mining activities and differentiating crop plants from weeds. This paper reviews several applications and works that have been made towards computer-based vision systems for automatic identification of plant species. It shows the various techniques alongside their descriptions. It portrays how future researchers in this field (especially precision agriculture or agricultural informatics) may move the knowledge domain forward.

Color of Salmon Fillets By Computer Vision and Sensory Panel

A computer vision method was developed and used to assign color score in salmon fillet according to SalmonFan™ card. The methodology was based on the transformation of RGB to L*a*b* color space. In the algorithm, RGB values assigned directly to each pixel by the camera in the salmon fillet image, were transformed to L*a*b* values, and then matched with other L*a*b* values that represent a SalmonFan score (between 20 and 34). Colors were measured by a computer vision system (CVS) and a sensorial panel (eight panelists) under the same illumination conditions in ten independent sets of experiments. Errors from transformation of RGB to L*a*b* values by the CVS were 2.7%, 1%, and 1.7%, respectively, with a general error range of 1.83%. The coefficient of correlation between the SalmonFan score assigned by computer vision and the sensory panel was 0.95. Statistical analysis using t test was performed and showed that there were no differences in the measurements of the SalmonFan score between both methods (tc = 1.65 ≤ t = 1.96 at α = 0.05%). The methodology presented in this paper is very versatile and can potentially be used by computer-based vision systems in order to qualify salmon fillets based on color according to the SalmonFan card.

Engineering Aspects of Production and Harvest Mechanization for Fresh and Processed Vegetables

Production and harvesting systems for processing vegetables have been highly mechanized, however, field efficiencies are generally low, and high field losses and fruit damage continue to limit profits for several crops. By comparison, the number of fresh market crops currently machine harvested is small, and research to develop new harvesting technology for these crops is limited. Current mechanization research includes improvements to existing production systems, development of harvesters for crops currently hand-harvested, and the integration of new technologies into current (and future) production systems. Mechanical harvester-based production systems are evolving that reduce field losses and fruit damage, improve recovery, and decrease the foreign materials in the harvested product. However, improved cultural production systems and crop varieties that are adapted for once-over machine harvest are needed. An integrated approach in which crop characteristics along with planting, cultivating, and harvesting techniques are considered will be necessary to develop profitable and highly efficient alternatives to hand-harvest production. The integration of new technologies including differential global positioning systems (DGPS), automatic machine guidance, and computer-based vision systems offers significant performance benefits, and is a substantial component of current vegetable production and harvesting research in the U.S. In time, as the costs of these technologies decline, commercial adoption of these new methods is expected to increase.

The Characterisation of the Static and Dynamic Drape of Fabrics

This paper discusses and establishes the static and dynamic drape of fabrics as an aesthetic property. A new algorithm is introduced, which defines more precisely the drapability of a given fabric. Experimental results show that it is more accurate to describe the different types of fabric-drape performance by using a feature vector, and this is found to be in good agreement with subjective assessment. A computer-based vision system, the Static- and Dynamic-drape-measurement System (M3), was developed and made possible the application of the new algorithm to actual fabric measurement. The results show agreement between aesthetic judgement and subjective assessment, and consequently fabric drape is standardised into four drape grades, ranging from high to low. The M3 is able to relate fabric drape with mechanical properties, simulating intelligence or expert knowledge when property change is needed for achieving a required drape performance.

A Low Cost Production Line Inspection System

Abstract The application of a computer based vision system in a high speed production line environment is described. Particular emphasis is placed on the need for a low cost solution which operates reliably in real-time, despite inherent implementation problems such as lighting. Comparisons are made between a number of different vision systems in terms of their performance and characteristics when trialled on the Brylcreem tub assembly, filling and packaging line at Maidenhead

Determination of the plastic zone by laser-speckle correlation

Laser-speckle-pattern correlation is used for the determination of elastic-plastic boundary on the surface of well polished metal specimens. The method employs a converging laser beam to illuminate the test object. Diffracted verging laser beam to illuminate the test object. Diffracted images are recorded and processed on a computer-based vision system. Subsequent image-correlation analysis yields information on the surface deformation of the test objects. The technique is applied to a flat tensile specimen with two circular notches at the central portion. Measured plastic zone is compared with results obtained by the finite-element method.