This paper describes the work that is done by a group of I3 students at Philips CFT in Eindhoven, Netherlands. I3 is an initiative of Fontys University of Professional Education also located in Eindhoven. The work focuses on the use of computer vision in motion control. Experiments are done with several techniques for object recognition and tracking, and with the guidance of a robot movement by means of computer vision. These experiments involve detection of coloured objects, object detection based on specific features, template matching with automatically generated templates, and interaction of a robot with a physical object that is viewed by a camera mounted on the robot.
DOCUMENT
This article deals with automatic object recognition. The goal is that in a certain grey-level image, possibly containing many objects, a certain object can be recognized and localized, based upon its shape. The assumption is that this shape has no special characteristics on which a dedicated recognition algorithm can be based (e.g. if we know that the object is circular, we could use a Hough transform or if we know that it is the only object with grey level 90, we can simply use thresholding). Our starting point is an object with a random shape. The image in which the object is searched is called the Search Image. A well known technique for this is Template Matching, which is described first.
DOCUMENT
Growing research in sign language recognition, generation, and translation AI has been accompanied by calls for ethical development of such technologies. While these works are crucial to helping individual researchers do better, there is a notable lack of discussion of systemic biases or analysis of rhetoric that shape the research questions and methods in the field, especially as it remains dominated by hearing non-signing researchers. Therefore, we conduct a systematic review of 101 recent papers in sign language AI. Our analysis identifies significant biases in the current state of sign language AI research, including an overfocus on addressing perceived communication barriers, a lack of use of representative datasets, use of annotations lacking linguistic foundations, and development of methods that build on flawed models. We take the position that the field lacks meaningful input from Deaf stakeholders, and is instead driven by what decisions are the most convenient or perceived as important to hearing researchers. We end with a call to action: the field must make space for Deaf researchers to lead the conversation in sign language AI.
LINK
Over the past few years a growing number of artists have critiqued the ubiquity of identity recognition technologies. Specifically, the use of these technologies by state security programs, tech-giants and multinational corporations has met with opposition and controversy. A popular form of resistance to recognition technology is sought in strategies of masking and camouflage. Zach Blas, Leo Selvaggio, Sterling Crispin and Adam Harvey are among a group of internationally acclaimed artists who have developed subversive anti-facial recognition masks that disrupt identification technologies. This paper examines the ontological underpinnings of these popular and widely exhibited mask projects. Over and against a binary understanding and criticism of identity recognition technology, I propose to take a relational turn to reimagine these technologies not as an object for our eyes, but as a relationship between living organisms and things. A relational perspective cuts through dualist and anthropocentric conceptions of recognition technology opening pathways to intersectional forms of resistance and critique. Moreover, if human-machine relationships are to be understood as coming into being in mutual dependency, if the boundaries between online and offline are always already blurred, if the human and the machine live intertwined lives and it is no longer clear where the one stops and the other starts, we need to revise our understanding of the self. A relational understanding of recognition technology moves away from a notion of the self as an isolated and demarcated entity in favour of an understanding of the self as relationally connected, embedded and interdependent. This could alter the way we relate to machines and multiplies the lines of flight we can take out of a culture of calculated settings.
DOCUMENT
Brochure from the Inauguration of Klaas Dijkstra, professor Computer Vision and Data Science
DOCUMENT
![I’M A.I. IMage Processing and Artificial Intelligence [Inaugurele rede]](https://publinova-harvester-content-prod.s3.amazonaws.com/thumbnails/files/previews/pdf/20250506132441657988.LS20Brochure20Professorship20CVDS20FINAL20WEB2028129-thumbnail-400x300.png)
Studying images in social media poses specific methodological challenges, which in turn have directed scholarly attention toward the computational interpretation of visual data. When analyzing large numbers of images, both traditional content analysis as well as cultural analytics have proven valuable. However, these techniques do not take into account the contextualization of images within a socio-technical environment. As the meaning of social media images is co-created by online publics, bound through networked practices, these visuals should be analyzed on the level of their networked contextualization. Although machine vision is increasingly adept at recognizing faces and features, its performance in grasping the meaning of social media images remains limited. Combining automated analyses of images with platform data opens up the possibility to study images in the context of their resonance within and across online discursive spaces. This article explores the capacities of hashtags and retweet counts to complement the automated assessment of social media images, doing justice to both the visual elements of an image and the contextual elements encoded through the hashtag practices of networked publics.
DOCUMENT
Background: Profiling the plant root architecture is vital for selecting resilient crops that can efficiently take up water and nutrients. The high-performance imaging tools available to study root-growth dynamics with the optimal resolution are costly and stationary. In addition, performing nondestructive high-throughput phenotyping to extract the structural and morphological features of roots remains challenging. Results: We developed the MultipleXLab: a modular, mobile, and cost-effective setup to tackle these limitations. The system can continuously monitor thousands of seeds from germination to root development based on a conventional camera attached to a motorized multiaxis-rotational stage and custom-built 3D-printed plate holder with integrated light-emitting diode lighting. We also developed an image segmentation model based on deep learning that allows the users to analyze the data automatically. We tested the MultipleXLab to monitor seed germination and root growth of Arabidopsis developmental, cell cycle, and auxin transport mutants non-invasively at high-throughput and showed that the system provides robust data and allows precise evaluation of germination index and hourly growth rate between mutants. Conclusion: MultipleXLab provides a flexible and user-friendly root phenotyping platform that is an attractive mobile alternative to high-end imaging platforms and stationary growth chambers. It can be used in numerous applications by plant biologists, the seed industry, crop scientists, and breeding companies.
LINK
The paper introduced an automatic score detection model using object detection techniques. The performance of sevenmodels belonging to two different architectural setups was compared. Models like YOLOv8n, YOLOv8s, YOLOv8m, RetinaNet-50, and RetinaNet-101 are single-shot detectors, while Faster RCNN-50 and Faster RCNN-101 belong to the two-shot detectors category. The dataset was manually captured from the shooting range and expanded by generating more versatile data using Python code. Before the dataset was trained to develop models, it was resized (640x640) and augmented using Roboflow API. The trained models were then assessed on the test dataset, and their performance was compared using matrices like mAP50, mAP50-90, precision, and recall. The results showed that YOLOv8 models can detect multiple objects with good confidence scores.
DOCUMENT
Many studies have shown that experts possess better perceptual-cognitive skills than novices (e.g., in anticipation, decision making, pattern recall), but it remains unclear whether a relationship exists between performance on those tests of perceptual-cognitive skill and actual on-field performance. In this study, we assessed the in situ performance of skilled soccer players and related the outcomes to measures of anticipation, decision making, and pattern recall. In addition, we examined gaze behaviour when performing the perceptual-cognitive tests to better understand whether the underlying processes were related when those perceptual-cognitive tasks were performed. The results revealed that on-field performance could not be predicted on the basis of performance on the perceptual-cognitive tests. Moreover, there were no strong correlations between the level of performance on the different tests. The analysis of gaze behaviour revealed differences in search rate, fixation duration, fixation order, gaze entropy, and percentage viewing time when performing the test of pattern recall, suggesting that it is driven by different processes to those used for anticipation and decision making. Altogether, the results suggest that the perceptual-cognitive tests may not be as strong determinants of actual performance as may have previously been assumed.
DOCUMENT
In recent years, drones have increasingly supported First Responders (FRs) in monitoring incidents and providing additional information. However, analysing drone footage is time-intensive and cognitively demanding. In this research, we investigate the use of AI models for the detection of humans in drone footage to aid FRs in tasks such as locating victims. Detecting small-scale objects, particularly humans from high altitudes, poses a challenge for AI systems. We present first steps of introducing and evaluating a series of YOLOv8 Convolutional Neural Networks (CNNs) for human detection from drone images. The models are fine-tuned on a created drone image dataset of the Dutch Fire Services and were able to achieve a 53.1% F1-Score, identifying 439 out of 825 humans in the test dataset. These preliminary findings, validated by an incident commander, highlight the promising utility of these models. Ongoing efforts aim to further refine the models and explore additional technologies.
MULTIFILE
