Affective Computing Archives - Tech4Animals

Automated Detection of Cat Facial Landmarks

annazam — Sat, 17 Aug 2024 08:10:19 +0000

This paper addresses the need for quality datasets in animal affective computing, focusing on cat facial expressions. It introduces CatFLW (Cat Facial Landmarks in the Wild), a dataset of 2091 cat facial images annotated with bounding boxes and 48 facial landmarks based on cat anatomy and the Cat Facial Action Coding System. The paper also presents the Ensemble Landmark Detector (ELD), a CNN model that outperforms other models on the CatFLW dataset and generalizes well to humans and other animals. This work advances automated pain and emotion recognition in cats by providing an explainable approach that connects landmark geometry to action units, overcoming limitations of manual analysis and “black box” deep learning methods.

The post Automated Detection of Cat Facial Landmarks appeared first on Tech4Animals.

Automated Analysis of Emotional Expressions in Dogs Based on Geometric Morphometrics

annazam — Tue, 02 Sep 2025 16:33:31 +0000

This paper presents the first fully automated analysis of dog facial expressions in a real-life fear context, specifically during New Year’s Eve fireworks compared to a control evening. Utilizing a novel AI-pipeline and a geometric morphometrics-inspired approach, the study analyzed 36 facial landmarks from owner-provided videos of a morphologically diverse sample of pet dogs in their home environment. The analysis revealed that backwards-drawn ears, indicated by ear base landmarks, were the most significant differentiator between the fireworks and control conditions, consistent with previous manual coding. Additionally, more mouth-opening, potentially reflecting panting, was associated with the firework condition. This pioneering work demonstrates that automated analysis of dog facial expressions is feasible even in challenging, noisy “in the wild” datasets, paving the way for objective, large-scale emotion detection to improve animal welfare assessment in clinical and behavioral settings.

The post Automated Analysis of Emotional Expressions in Dogs Based on Geometric Morphometrics appeared first on Tech4Animals.

Does the Tail Show When the Nose Knows? Artificial intelligence outperforms human experts at predicting detection dogs finding their target through tail kinematics

annazam — Wed, 13 Aug 2025 08:26:24 +0000

This study investigated whether artificial intelligence (AI) could predict when detection dogs found a target odour based on their tail movements, comparing AI performance to that of human experts. Using computer vision and markerless tracking on top-view videos, researchers analyzed tail kinematic patterns of eight dogs during a scent detection task, which included a trained odour concentration (Test 1) and progressively lower concentrations (Test 2). While kinematic analyses showed only modest group-level differences in tail-wagging, with dogs exhibiting a higher left-sided tail-wagging amplitude in the target odour area in Test 1, and lower right-sided wagging in Test 2, some individual dogs displayed distinct patterns. An AI model achieved a 77% accuracy in classifying whether dogs were in the target odour area in Test 1, with its performance decreasing at lower odour concentrations in Test 2, mirroring the dogs’ struggles. Crucially, when compared to 190 detection dog handlers on a subset of videos, the AI model significantly outperformed human professionals, correctly classifying 66% of videos versus 46% for experts. These findings highlight the potential of AI-enhanced techniques to offer new insights into canine behaviour during odour discrimination and could lead to improved detection dog training by providing objective behavioral cues.

The post Does the Tail Show When the Nose Knows? Artificial intelligence outperforms human experts at predicting detection dogs finding their target through tail kinematics appeared first on Tech4Animals.

Non-Invasive Computer Vision-Based Fruit Fly Larvae Differentiation: Ceratitis capitata and Bactrocera zonata

annazam — Mon, 08 Sep 2025 14:14:24 +0000

This paper proposes a novel, non-invasive method using computer vision and AI for the rapid differentiation between larvae of the Mediterranean fruit fly (Ceratitis capitata) and the peach fruit fly (Bactrocera zonata), two economically significant agricultural pests. Due to their visual similarity, traditional DNA-based detection is costly and time-consuming, while manual morphological identification is practically impossible. The proposed solution employs a two-module AI pipeline: a point representation extraction module that uses YOLOv8 to track larval contours and extract either a center of mass or 2-ellipse foci, followed by a time series analysis module utilizing a Clockwork Recurrent Neural Network to classify larval movement patterns. Using 15-second video recordings of single larvae moving on Petri dishes, the method achieved good separation between the two species, with 90% accuracy. Specifically, the Dual Ellipses approach achieved an accuracy of 90.4%, with a sensitivity of 93.4% and an F1 Score of 90.7%. This system aims to provide a rapid, cost-effective, and scalable solution to complement existing detection methods, enhancing agricultural biosecurity.

The post Non-Invasive Computer Vision-Based Fruit Fly Larvae Differentiation: Ceratitis capitata and Bactrocera zonata appeared first on Tech4Animals.

Investigating the Capabilities of Large Vision Language Models in Dog Emotion Recognition

annazam — Fri, 21 Nov 2025 15:29:02 +0000

This study evaluates the ability of large vision-language models, such as GPT-4o and Gemini, to accurately identify dog emotions from images. Researchers discovered that these AI systems frequently rely on superficial contextual cues, such as the background environment, rather than the animal’s actual biological signals. When tested on scientifically controlled datasets featuring cropped facial expressions and minimal scenery, the models’ performance plummeted to near-chance levels. These results suggest that current AI carries significant anthropocentric biases and often misinterprets canine internal states based on human-centric assumptions. Consequently, the authors argue for a more interdisciplinary approach that integrates validated behavioral science to improve animal-centered artificial intelligence. Through background manipulation and prompt testing, the paper highlights the technical and ethical risks of using general-purpose models for veterinary or animal welfare assessments.

The post Investigating the Capabilities of Large Vision Language Models in Dog Emotion Recognition appeared first on Tech4Animals.

A Segment-based Framework for Explainability in Animal Affective Computing

annazam — Mon, 21 Jul 2025 11:49:09 +0000

This paper introduces a novel segment-based framework for enhancing the explainability of deep learning models in animal affective computing, a field that uses technology to understand animal emotions. The core challenge addressed is the “black box” nature of deep learning, which makes it difficult to understand why a model makes a particular decision, hindering trust and adoption among researchers. The proposed framework focuses on evaluating visual explanations, specifically saliency maps, by quantifiably assessing how well they align with biologically meaningful semantic parts of an animal, such as eyes, ears, and mouth. Through case studies on cat pain, horse pain, and dog emotions, the authors demonstrate how this framework can provide quantifiable insights into which facial regions are most important for a classifier’s decision, revealing that the eye area consistently holds the most significance. Ultimately, this framework aims to bridge the gap between complex AI models and expert knowledge, fostering both validation of known indicators and the discovery of new ones in animal behavior.

The post A Segment-based Framework for Explainability in Animal Affective Computing appeared first on Tech4Animals.

Automated Facial Landmark Analysis vs. Manual Coding: Accuracy in Dog Emotional Expression Classification

annazam — Fri, 24 Oct 2025 11:46:04 +0000

Assessing animal emotions is critical for welfare, yet reliable, objective indicators of canine fear remain debated. To address this gap, this study used machine learning to classify firework-related fear in dogs, comparing traditional manual behavioral coding with automated facial landmark analysis. Models were trained on videos of dogs experiencing calm baseline conditions versus stressful fireworks. While both approaches successfully detected distress, the model based on manual ethogram coding achieved the highest accuracy. It highlighted backwards-directed ears and increased blinking as the strongest predictors of fear. Notably, the machine learning algorithms recognized blinking as a key behavioral cue that traditional statistical analyses had previously overlooked.

The post Automated Facial Landmark Analysis vs. Manual Coding: Accuracy in Dog Emotional Expression Classification appeared first on Tech4Animals.

Automated Recognition of Emotional States of Horses from Facial Expressions

annazam — Wed, 31 Jul 2024 02:45:23 +0000

This research introduces the first automated recognition of emotional states in horses from facial expressions, moving beyond the typical focus on pain in animal affective computing. The study, conducted by Marcelo Feighelstein, Claire Riccie-Bonot, and their colleagues, developed two AI models: a deep learning model that analyzes video footage and a machine learning model that uses EquiFACS annotations. The video-based model achieved a higher accuracy of 76% in distinguishing four emotional states: baseline, positive anticipation, disappointment, and frustration, indicating that raw video data may contain more nuanced information than manual coding. While the deep learning approach offers superior performance, the EquiFACS-based model provides greater interpretability through its decision tree structure, offering insights into the specific facial cues driving its classifications.

The post Automated Recognition of Emotional States of Horses from Facial Expressions appeared first on Tech4Animals.

From Data to Dialogue: A Multi-Agent Chatbot Interface for Decision Support in Guide Dog Training

annazam — Sun, 22 Mar 2026 14:17:05 +0000

Guide dog training programs collect extensive behavioral and performance data, but trainers often struggle to utilize this information because it is locked in complex databases requiring technical expertise. To bridge this gap, this study introduces a multi-agent conversational chatbot that helps trainers easily access and interpret data about guide dogs. Using natural language queries, handlers can connect to a machine learning pipeline to compare historical records and predict training outcomes. An evaluation with professional trainers demonstrated that this dialogue-based interface made the underlying behavioral information highly approachable and interpretable. Ultimately, the system transforms scattered technical metrics into actionable insights, successfully empowering trainers to make practical, data-driven decisions.

The post From Data to Dialogue: A Multi-Agent Chatbot Interface for Decision Support in Guide Dog Training appeared first on Tech4Animals.

Non-invasive Canine Electroencephalography (EEG): a systematic review

annazam — Tue, 18 Feb 2025 07:47:18 +0000

This research paper provides a systematic review of non-invasive electroencephalography (EEG) studies conducted on canines. It examines 22 studies to organize existing knowledge regarding methods, findings, and prevalent trends in canine cognitive neuroscience using EEG. The authors discuss the technical setups, data acquisition, and analysis frameworks employed in these studies, highlighting insights gained from awake and sleeping dog EEG recordings. Furthermore, the review identifies unexplored research questions, proposes standardization for methods and data structures, and suggests avenues for improving signal quality in future canine EEG research.

The post Non-invasive Canine Electroencephalography (EEG): a systematic review appeared first on Tech4Animals.