Advances In Machine Vision Research Articles

Prototyping and evaluation of a novel machine vision system for real-time, automated quality grading of sweetpotatoes

Rapid advances in machine vision and artificial intelligence (AI) technologies have generated high interest in developing automated grading and sorting solutions for fresh produce of specialty crops. Sweetpotatoes are an economically important crop in the United States and beyond, but grading and sorting the commodity, especially for surface defects, remains a labor-intensive operation at commercial packing facilities. In addition to incurring high labor costs, manual grading is subjective and prone to human assessment error. This study was therefore aimed to develop automated grading technology based on machine vision and state-of-the-art AI to reduce labor dependence and improve quality assessment for sweetpotato packing lines. The developed grading system prototype consisted of a custom-designed roller conveyor to transport and rotate sweetpotatoes and an overhead color camera to perform full-surface quality assessment for size and surface defects. A YOLOv8-based computer vision pipeline was developed to segment and track each sweetpotato traveling on the conveyor and analyze sample quality conditions in real-time. The YOLOv8l model coupled with the BoT-SORT tracker achieved the overall Higher Order Tracking Accuracy (HOTA) score of 0.952. Based on the instance segmentation by YOLOv8l, the length and width of sweetpotatoes were estimated with percentage accuracies of 96.7 % and 90.3 %, respectively, while the instance segmentation for three classes of sweetpotatoes according to surface defect conditions yielded an overall accuracy of 82.6 %, regardless of samples. The final sample grading, which was realized by taking into account the quality information recorded from a sequence of multi-view images for each sample, achieved an overall accuracy of 91.7 % in grading four classes of sweetpotatoes. The developed prototype holds promise for next-stage integration with sorting mechanisms into a full-fledged sorting system and will be eventually beneficial for sweetpotatoes packers.

Artificial intelligence-based spatio-temporal vision sensors: applications and prospects

Introduction: Advances in machine vision and mobile electronics will be accelerated by the creation of sophisticated optoelectronic vision sensors that allow for sophisticated picture recognition of visual information and data pre-processing. Several new types of vision sensors have been devised in the last decade to solve these drawbacks, one of which is neuromorphic vision sensors, which have exciting qualities such as high temporal resolution, broad dynamic range, and low energy consumption. Neuromorphic sensors are inspired by the working principles of biological sensory neurons and would be useful in telemedicine, health surveillance, security monitoring, automatic driving, intelligent robots, and other applications of the Internet of Things.Methods: This paper provides a comprehensive review of various state-of-the-art AI vision sensors and frameworks.Results: The fundamental signal processing techniques deployed and the associated challenges were discussed.Discussion: Finally, the role of vision sensors in computer vision is also discussed.

Canonical circuit computations for computer vision.

Advanced computer vision mechanisms have been inspired by neuroscientific findings. However, with the focus on improving benchmark achievements, technical solutions have been shaped by application and engineering constraints. This includes the training of neural networks which led to the development of feature detectors optimally suited to the application domain. However, the limitations of such approaches motivate the need to identify computational principles, or motifs, in biological vision that can enable further foundational advances in machine vision. We propose to utilize structural and functional principles of neural systems that have been largely overlooked. They potentially provide new inspirations for computer vision mechanisms and models. Recurrent feedforward, lateral, and feedback interactions characterize general principles underlying processing in mammals. We derive a formal specification of core computational motifs that utilize these principles. These are combined to define model mechanisms for visual shape and motion processing. We demonstrate how such a framework can be adopted to run on neuromorphic brain-inspired hardware platforms and can be extended to automatically adapt to environment statistics. We argue that the identified principles and their formalization inspires sophisticated computational mechanisms with improved explanatory scope. These and other elaborated, biologically inspired models can be employed to design computer vision solutions for different tasks and they can be used to advance neural network architectures of learning.

A review of machine learning and satellite imagery for poverty prediction: Implications for development research and applications

AbstractThe field of artificial intelligence is seeing the increased application of satellite imagery to analyse poverty in its various manifestations. This nascent but rapidly growing intersection of scholarship holds the potential to help us better understand poverty by leveraging big data and recent advances in machine vision. In this study, we statistically analyse the literature in the expanding field of welfare and poverty predictions from the combination of machine learning and satellite imagery. Here, we apply an integrative review method to extract key data on factors related to the predictive power of welfare. We found that the most important factors correlated to the predictive power of welfare are the number of pre‐processing steps employed, the number of datasets used, the type of welfare indicator targeted and the choice of AI model. Studies that used stock measure indicators (assets) as targets achieved better performance—17 percentage points higher—in predicting welfare than those that targeted flow measures (income and consumption) ones. Additionally, we found that the combination of machine learning and deep learning significantly increases predictive power—by as much as 15 percentage points—compared to using either alone. Surprisingly, we found that the spatial resolution of the satellite imagery used is important but not critical to the performance as the relationship is positive but not statistically significant. These findings have important implications for future research in this domain and for anyone aspiring to use the methodology.

Comparative Analysis of Detectors and Feature Descriptors for Multispectral Image Matching in Rice Crops.

Precision agriculture has greatly benefited from advances in machine vision and image processing techniques. The use of feature descriptors and detectors allows to find distinctive keypoints in an image and the use of this approach for agronomical applications has become a widespread field of study. By combining near infrared (NIR) images, acquired with a modified Nikon D80 camera, and visible spectrum (VIS) images, acquired with a Nikon D300s, a proper crop identification could be obtained. Still, the use of different sensors brings an image matching challenge due to the difference between cameras and the possible distortions from each imaging technique. The aim of this paper is to compare the performance of several feature descriptors and detectors by comparing near infrared and visual spectral bands in rice crop images. Therefore, a group of 20 different scenes with different cameras and growth stages in a rice crop were evaluated. Thus, red, green, blue (RGB) and L, a, b (CIE L*a*b*) channels were extracted from VIS images in order to compare the matches obtained between each of them and the corresponding NIR image. The BRISK, SURF, SIFT, ORB, KAZE, and AKAZE methods were implemented, which act as descriptors and detectors. Additionally, a combination was made between the FAST algorithm for the detection of keypoints with the BRIEF, BRISK, and FREAK methods for features description. BF and FLANN matching methods were used. The algorithms were implemented in Python using OpenCV library. The green channel presented the highest number of correct matches in all methods. In turn, the method that presented the highest performance both in time and in the number of correct matches was the combination of the FAST feature detector and the BRISK descriptor.

WormPose: Image synthesis and convolutional networks for pose estimation in C. elegans.

An important model system for understanding genes, neurons and behavior, the nematode worm C. elegans naturally moves through a variety of complex postures, for which estimation from video data is challenging. We introduce an open-source Python package, WormPose, for 2D pose estimation in C. elegans, including self-occluded, coiled shapes. We leverage advances in machine vision afforded from convolutional neural networks and introduce a synthetic yet realistic generative model for images of worm posture, thus avoiding the need for human-labeled training. WormPose is effective and adaptable for imaging conditions across worm tracking efforts. We quantify pose estimation using synthetic data as well as N2 and mutant worms in on-food conditions. We further demonstrate WormPose by analyzing long (∼ 8 hour), fast-sampled (∼ 30 Hz) recordings of on-food N2 worms to provide a posture-scale analysis of roaming/dwelling behaviors.

Plant Disease Detection and Classification Using Image Processing and Neural Networks

Plant disease is a major problem for food security, but in many parts of the world their rapid prediction remains difficult because of lack of the infrastructure required. New advances in machine vision achieved via deep learning have paved the way for diagnosis of AI-assisted diseases. To help determine the extent of plant disease, provide agricultural specialists with a digital archive with photos of diseased leaves. Estimate depends on Standard Area Diagrams (SADs), a collection of diseased leaf images, each of which includes an incrementally more diseased leaf compared to the previous one. Every SAD shows seriousness of the disease in terms of the percentage of the diseased leaf. Users then turn to the field for a leaf. For eg, equate it to SADs and use it to measure the severity of the disease. “This app is useful for crop consultants and research scientists looking to cut costs and improve the time and accuracy for assessing disease severity in plants.”

ПОВЫШЕНИЕ ЭФФЕКТИВНОСТИ ПРОЦЕССОВ ПРОИЗДВОДСТВА ДРЕВЕСНОЙ ЩЕПЫ

The paper presents a novel approach to the problem of utilizing wood chips as a valuable raw material. It shows how advances in machine vision can enable the conversion of wood chips from waste to a valuable resource. Empirical dependencies that are used to calculate the slip velocity of wood chips on the walls of the tank have been obtained. The problems of particle–fluid and particle–particle interactions within the flow are solved. Findings may be applied not only in countries with traditionally developed wood industries but also in many others.

Image Captioning using Facial Expression and Attention

Benefiting from advances in machine vision and natural language processing techniques, current image captioning systems are able to generate detailed visual descriptions. For the most part, these descriptions represent an objective characterisation of the image, although some models do incorporate subjective aspects related to the observer’s view of the image, such as sentiment; current models, however, usually do not consider the emotional content of images during the caption generation process. This paper addresses this issue by proposing novel image captioning models which use facial expression features to generate image captions. The models generate image captions using long short-term memory networks applying facial features in addition to other visual features at different time steps. We compare a comprehensive collection of image captioning models with and without facial features using all standard evaluation metrics. The evaluation metrics indicate that applying facial features with an attention mechanism achieves the best performance, showing more expressive and more correlated image captions, on an image caption dataset extracted from the standard Flickr 30K dataset, consisting of around 11K images containing faces. An analysis of the generated captions finds that, perhaps unexpectedly, the improvement in caption quality appears to come not from the addition of adjectives linked to emotional aspects of the images, but from more variety in the actions described in the captions.

Emerging Advances to Transform Histopathology Using Virtual Staining.

In an age where digitization is widespread in clinical and preclinical workflows, pathology is still predominantly practiced by microscopic evaluation of stained tissue specimens affixed on glass slides. Over the last decade, new high throughput digital scanning microscopes have ushered in the era of digital pathology that, along with recent advances in machine vision, have opened up new possibilities for Computer-Aided-Diagnoses. Despite these advances, the high infrastructural costs related to digital pathology and the perception that the digitization process is an additional and nondirectly reimbursable step have challenged its widespread adoption. Here, we discuss how emerging virtual staining technologies and machine learning can help to disrupt the standard histopathology workflow and create new avenues for the diagnostic paradigm that will benefit patients and healthcare systems alike via digital pathology.

Effect of Visual and Auditory Alerts on Older Drivers’ Glances toward Latent Hazards while Turning Left at Intersections

Older drivers are known to make significantly fewer glances toward hazards that are hidden from view (latent hazards) than middle-aged drivers. This is especially true when the driver is making a left turn at an intersection at that critical point in the turn immediately after the driver enters the intersection. This has led to the development of training programs that can increase the frequency of these glances toward latent hazards at intersections. However, training programs can require time and money that many older adults may not have. Advances in machine vision and vehicle-to-vehicle communications technologies make possible the use of alerts that warn older drivers of the location of latent hazards at intersections. This driving simulator study investigates the effect of auditory and visual warning alerts on older drivers’ primary (before entering the intersection) and secondary (just after entering the intersection) glance behavior when making a left turn at an intersection. In a between-subjects design, forty older drivers navigated eight unique scenarios containing latent hazards either in the presence or in the absence of combined auditory and visual hazard warning alerts. The results showed that older drivers anticipated a significantly greater proportion of latent hazards in the presence of warning alerts both before they enter the intersection and after they enter the intersection. The results of this study suggest that a combination of auditory and visual alerts may be effective at improving older drivers’ glance behavior while making left turns at intersections.

Advances in machine vision for flexible feeding of assembly parts

Human-robot collaboration can be used to share workload to form semi-automated production systems. Assembly operations are recognized with high potential to increase productivity by using the best skills of humans and robots in a combination. Components and parts to be assembled need to be structured and presented to the robot in a known location and orientation. The process of presenting parts to the robot for assembly tasks is referred to as parts feeding. Feeding system needs to be adaptable to dynamics of parts’ design, shape, location, and orientation to have flexibility in the production. The traditional automation methods for parts feeding are part-specific mechanical devices e.g. vibratory bowl feeders which are inflexible towards part variations. This comes as a hindrance in getting maximum advantage of the flexibility potential of human-robot collaboration in assembly. The recent years have seen advances in machine vision and has potential for feeding applications. This paper explores the developments in machine-vision for flexible feeding systems for human-robot assembly cells. A specification model is presented to develop a vision-guided flexible feeding system. Various vision-based feeding techniques are discussed and validated through an industrial case study. The results helped to compare the efficiency of each feeding technique for industrial application.

Humans, but Not Deep Neural Networks, Often Miss Giant Targets in Scenes

Even with great advances in machine vision, animals are still unmatched in their ability to visually search complex scenes. Animals from bees [1, 2] to birds [3] to humans [4-12] learn about the statistical relations in visual environments to guide and aid their search for targets. Here, we investigate a novel manner in which humans utilize rapidly acquired information about scenes by guiding search toward likely target sizes. We show that humans often miss targets when their size is inconsistent with the rest of the scene, even when the targets were made larger and more salient and observers fixated the target. In contrast, we show that state-of-the-art deep neural networks do not exhibit such deficits in finding mis-scaled targets but, unlike humans, can be fooled by target-shaped distractors that are inconsistent with the expected target's size within the scene. Thus, it is not a human deficiency to miss targets when they are inconsistent in size with the scene; instead, it is a byproduct of a useful strategy that the brain has implemented to rapidly discount potential distractors.

IPathology: Robotic Applications and Management of Plants and Plant Diseases

The rapid development of new technologies and the changing landscape of the online world (e.g., Internet of Things (IoT), Internet of All, cloud-based solutions) provide a unique opportunity for developing automated and robotic systems for urban farming, agriculture, and forestry. Technological advances in machine vision, global positioning systems, laser technologies, actuators, and mechatronics have enabled the development and implementation of robotic systems and intelligent technologies for precision agriculture. Herein, we present and review robotic applications on plant pathology and management, and emerging agricultural technologies for intra-urban agriculture. Greenhouse advanced management systems and technologies have been greatly developed in the last years, integrating IoT and WSN (Wireless Sensor Network). Machine learning, machine vision, and AI (Artificial Intelligence) have been utilized and applied in agriculture for automated and robotic farming. Intelligence technologies, using machine vision/learning, have been developed not only for planting, irrigation, weeding (to some extent), pruning, and harvesting, but also for plant disease detection and identification. However, plant disease detection still represents an intriguing challenge, for both abiotic and biotic stress. Many recognition methods and technologies for identifying plant disease symptoms have been successfully developed; still, the majority of them require a controlled environment for data acquisition to avoid false positives. Machine learning methods (e.g., deep and transfer learning) present promising results for improving image processing and plant symptom identification. Nevertheless, diagnostic specificity is a challenge for microorganism control and should drive the development of mechatronics and robotic solutions for disease management.

CPU, GPU and FPGA Implementations of MALD: Ceramic Tile Surface Defects Detection Algorithm

This paper addresses adjustments, implementation and performance comparison of the Moving Average with Local Difference (MALD) method for ceramic tile surface defects detection. Ceramic tile production process is completely autonomous, except the final stage where human eye is required for defects detection. Recent computational platform development and advances in machine vision provides us with several options for MALD algorithm implementation. In order to exploit the shortest execution time for ceramic tile production process, the MALD method is implemented on three different platforms: CPU, GPU and FPGA, and it is implemented on each platform in at least two ways. Implementations are done in MATLAB's MEX/C++, C++, CUDA/C++, VHDL and Assembly programming languages. Execution times are measured and compared for different algorithms and their implementations on different computational platforms.

Control of tracking systems by image correlation

SUMMARYOwing to advances in machine vision, it is now possible to study automatic gripping of moving parts. This complex task requires a precise knowledge of the displacements of objects in a camera field.In this paper, a method to analyse the motion of parts is presented; it is based on the correlation of numerical images. The treatment of data provided by the image background makes this method quite original.The utilization of this method, often considered as rather awkward, makes it possible, in this case, to develop a position feedback operation of the robot actuators controlled in an open loop (step by step motors).

Line Scan Vision System

The automation of inspection tasks has always been of prime concern to process engineers. Until recently, the technology was not available to automate anything but the simplest tasks. With advances in machine vision and computer technologies, many visual inspection tasks can now be automated. This paper describes an AT&T development that can be used as an efficient tool for automating the inspection of printed circuit board assemblies. Significant increases in reliability are achievable as compared to current methods, namely human inspectors.