Cats Archives - Tech4Animals

Computational Investigation of the Social Function of Domestic Cat Facial Signals

annazam — Sun, 04 Aug 2024 17:31:01 +0000

This paper explores the intricate social function of domestic cat facial signals, moving beyond traditional studies focused on pain to delve into their role in intraspecific interactions. Researchers utilized computational methods to develop machine learning classifiers capable of distinguishing between affiliative (friendly) and non-affiliative (less friendly) cat interactions. They found that models leveraging manual CatFACS codings were highly accurate, achieving over 77% accuracy when incorporating temporal information about facial movements. While a fully automated landmark-based approach showed lower accuracy (68%), it represents a promising, human-independent avenue for future analysis. A significant discovery was that domestic cats exhibit rapid facial mimicry, where one cat quickly matches another’s facial signal after observing it. This mimicry was notably more common in affiliative contexts, with specific ear movements (like EAD103 and EAD104) being particularly prone to this behavior. The findings suggest that rapid facial mimicry in cats, much like in other mammals, likely facilitates social bonding and helps coordinate behaviors, especially during social play, offering valuable insights for pet owners and rescue organizations seeking to strengthen cat relationships.

The post Computational Investigation of the Social Function of Domestic Cat Facial Signals appeared first on Tech4Animals.

Automated Video-based Pain Recognition in Cats using Facial Landmarks

annazam — Fri, 16 Aug 2024 20:33:48 +0000

This paper introduces a significant advancement in automated video-based pain recognition in cats by presenting an end-to-end artificial intelligence (AI) pipeline that requires no manual efforts in selecting suitable images or annotating facial landmarks. Unlike previous approaches that relied on static single images, this new pipeline works with raw video input, optimizing the capture of the temporal dimension of visual information, which is critical for accurate pain detection. The AI pipeline first automatically produces 48 cat facial landmarks on each video frame, then uses this time-series signal to predict the presence of cat pain. Tested on two different cat pain datasets, Finka et al. and TiHo Cat Pain, the pipeline achieved over 70% and 66% accuracy respectively, notably outperforming previous automated landmark-based methods that used single frames, thereby indicating that dynamics matter in cat pain recognition. The study also defines metrics to measure deficiencies in video datasets, such as occluded faces or inaccurate landmark detection, and investigates their impact on performance. The research highlights the potential for practical applications, like mobile apps for use in clinical settings or by pet owners, similar to human pain assessment tools, though further work is needed to address dataset diversity and real-time computational efficiency.

The post Automated Video-based Pain Recognition in Cats using Facial Landmarks appeared first on Tech4Animals.

Explainable Automated Pain Recognition in Cats

annazam — Wed, 16 Aug 2023 21:03:28 +0000

This study investigated the feasibility of automated pain recognition in cats using AI models in a more realistic and heterogeneous setting. Researchers compared two approaches: a landmark-based (LDM) approach utilizing 48 manually annotated facial landmarks, and a deep learning (DL) approach (ResNet50), on a dataset of 84 client-owned cats of diverse breeds, ages, sexes, and medical histories, with pain levels scored by veterinary experts. The findings showed that the landmark-based approach performed better, achieving over 77% accuracy in pain detection, while the deep learning approach reached only above 65%. This suggests that the LDM approach is more robust for noisier, naturalistic populations, possibly because it better accounts for variability in cat facial morphology. Furthermore, using explainable AI methods, the study consistently revealed across both approaches that the mouth region was most important for machine pain classification, whereas the ears region was least important. The study acknowledged limitations, including the dataset size and the use of static images, suggesting future research should focus on larger datasets, video-based analysis, and the automation of facial landmark detection. The results ultimately support that AI-assisted recognition of negative affective states like pain from cat faces is feasible, although these tools should complement, not replace, clinical judgment.

The post Explainable Automated Pain Recognition in Cats appeared first on Tech4Animals.

Catflw: Cat facial landmarks in the wild dataset

annazam — Wed, 16 Aug 2023 21:06:06 +0000

This paper introduces the Cat Facial Landmarks in the Wild (CatFLW) dataset, which aims to address the significant lack of datasets for automated facial analysis in animals, particularly for recognizing internal states like pain and emotions. The CatFLW dataset comprises 2016 images of cat faces captured in various environments and conditions, each annotated with 48 specific facial landmarks. These landmarks were carefully selected based on their relationship with underlying musculature and their relevance to cat-specific Facial Action Units (CatFACS), making them reliable for pain recognition. The dataset was created using a semi-supervised, human-in-the-loop (AI-assisted) annotation method, which significantly reduced the time required for annotation compared to purely manual approaches. By providing the largest available amount of cat facial landmarks, the CatFLW dataset is intended to advance automatic detection of pain and emotions in cats and serve as a foundational resource for developing similar datasets for other animal species.

The post Catflw: Cat facial landmarks in the wild dataset appeared first on Tech4Animals.

Automated Recognition of Pain in Cats

annazam — Sat, 20 Aug 2022 12:10:41 +0000

This paper presents the first comparative study on automated pain recognition in domestic short-haired cats using facial images. The researchers compared two distinct approaches: one utilizing convolutional neural networks (ResNet50) that take raw images as input, and another employing machine learning models based on 48 geometric facial landmarks, inspired by the catFACS system. Data was collected from 29 cats undergoing ovariohysterectomy at various time points corresponding to different pain intensities, with a final balanced dataset of 464 images from 26 cats classified as ‘Pain’ or ‘No Pain’. Both approaches demonstrated comparable accuracy of above 72% in classifying pain, indicating their potential for automated cat pain detection. The study concludes that the information contained within the 48 selected geometric facial landmarks is sufficient for pain classification, yielding accuracy similar to deep learning models that process raw image data. While this represents a significant step forward, the authors note that further methodological improvements, such as incorporating additional behavioral information and including more diverse cat populations, are necessary for real-world application and to increase generalizability and robustness.

The post Automated Recognition of Pain in Cats appeared first on 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.

Close Encounters of the Cat Kind: The influence of context and sex on facial signaling proximity in domesticated cats (Felis silvestris catus)

annazam — Wed, 01 Apr 2026 12:42:59 +0000

Accurately measuring animal social bonds often relies on analyzing spatial proximity, yet advanced automated tracking methods have rarely been applied to feline interactions. To address this gap, this study utilized AI-based computer vision systems to extract precise distance data from video recordings of domestic cats engaging in social facial signaling. Contrary to initial predictions, the analysis revealed that cats maintained significantly closer physical proximity during non-affiliative encounters than during friendly, affiliative interactions. Additionally, the sex of the interacting pairs strongly influenced their spacing, with female-female dyads staying the closest across all contexts. Ultimately, this work demonstrates how machine learning tools can uncover nuanced behavioral strategies that animals use to navigate social environments.

The post Close Encounters of the Cat Kind: The influence of context and sex on facial signaling proximity in domesticated cats (Felis silvestris catus) appeared first on Tech4Animals.

Supervised Neural Style Transfer as an Augmentation Technique for Facial Landmark Detection

annazam — Tue, 07 Apr 2026 13:20:48 +0000

A major challenge in training accurate facial landmark detection models for animals is the scarcity of diverse data, as classical image augmentations often disrupt the crucial spatial alignments required for this task. To address this gap, this study introduces a novel data augmentation technique called Supervised Neural Style Transfer (SNST). Focusing on cats, the researchers synthetically expanded their training dataset by transferring textural styles from top-performing examples onto cropped facial images, which perfectly preserved the original geometric structure of the faces. This specific approach effectively decouples appearance from shape, forcing the models to rely on robust structural features rather than surface-level textures. Ultimately, the study demonstrates that SNST significantly outperforms traditional augmentation methods, substantially reducing detection errors and improving the models’ overall robustness.

The post Supervised Neural Style Transfer as an Augmentation Technique for Facial Landmark Detection appeared first on Tech4Animals.

Semantic Style Transfer for Enhancing Animal Facial Landmark Detection

annazam — Sun, 20 Jul 2025 13:46:18 +0000

This study explores semantic style transfer to enhance animal facial landmark detection, focusing on cat faces as a case study. The researchers demonstrate that cropping facial images before applying style transfer significantly improves the quality and structural consistency of generated images. Furthermore, while training models solely on style-transferred images can degrade performance, Supervised Style Transfer (SST), which selects style sources based on landmark accuracy, effectively mitigates this issue. Ultimately, augmenting existing datasets with these carefully curated, style-transferred images proves to be a powerful data augmentation strategy, outperforming traditional methods and improving the robustness and accuracy of facial landmark detection models for animals.

The post Semantic Style Transfer for Enhancing Animal Facial Landmark Detection appeared first on Tech4Animals.

Automated Landmark-based Cat Facial Analysis and its Applications

annazam — Sat, 03 Aug 2024 06:49:35 +0000

This paper systematically explores the utility of an automated 48-landmark detector for cat facial analysis, addressing the labor-intensive nature of manual annotation. The study developed AI pipelines for three benchmark tasks using two previously collected datasets: cat breed recognition, cephalic type recognition, and pain recognition. While replacing manual landmarks with automated ones generally decreased performance across all tasks, this reduction was an acceptable trade-off for full automation in some areas. Specifically, automated pipelines achieved 75% accuracy in cephalic type recognition and 66% in pain recognition, suggesting landmark-based approaches show promise for automated pain assessment and morphological explorations. However, the breed recognition pipeline performed poorly, indicating that deep learning approaches using direct image data might be more suitable for this task. The study emphasizes the need for valid benchmarks and publicly accessible datasets in animal facial analysis, similar to human affective computing, while also considering ethical implications.

The post Automated Landmark-based Cat Facial Analysis and its Applications appeared first on Tech4Animals.