Triplet Transform Learning for Automated Primate Face Recognition
01 Sep 2019-pp 3462-3466
TL;DR: A novel Triplet Transform Learning (TTL) model for learning discriminative representations of primate faces is proposed, where it outperforms the existing approaches and attains state-of-the-art performance on the primates database.
Abstract: Automated primate face recognition has enormous potential in effective conservation of species facing endangerment or extinction. The task is characterized by lack of training data, low inter-class variations, and large intra-class differences. Owing to the challenging nature of the problem, limited research has been performed to automate the process of primate face recognition. In this research, we propose a novel Triplet Transform Learning (TTL) model for learning discriminative representations of primate faces. The proposed model reduces the intra-class variations and increases the inter-class variations to obtain robust sparse representations for the primate faces. It is utilized to present a novel framework for primate face recognition, which is evaluated on the primate dataset, comprising of 80 identities including monkeys, gorillas, and chimpanzees. Experimental results demonstrate the efficacy of the proposed approach, where it outperforms the existing approaches and attains state-of-the-art performance on the primates database.
Citations
More filters
TL;DR: The proposed method, NOvel Ringed seal re-identification by Pelage Pattern Aggregation (NORPPA), utilizes the permanent and unique pelage pattern of Saimaa ringed seals and content-based image retrieval techniques and is shown to produce the best re- identity accuracy on the dataset in comparisons with alternative approaches.
Abstract: We propose a method for Saimaa ringed seal ( Pusa hispida saimensis ) re-identification. Access to large image volumes through camera trapping and crowdsourcing provides novel possibilities for animal monitoring and conservation and calls for automatic methods for analysis, in particular, when re-identifying individual animals from the images. The proposed method NOvel Ringed seal re-identification by Pelage Pattern Aggregation (NORPPA) utilizes the permanent and unique pelage pattern of Saimaa ringed seals and content-based image retrieval techniques. First, the query image is preprocessed, and each seal instance is segmented. Next, the seal’s pelage pattern is extracted using a U-net encoder-decoder based method. Then, CNN-based affine invariant features are embedded and aggregated into Fisher Vectors. Finally, the cosine distance between the Fisher Vectors is used to find the best match from a database of known individuals. We perform extensive experiments of various modifications of the method on a new challenging Saimaa ringed seals re-identification dataset. The proposed method is shown to produce the best re-identification accuracy on our dataset in comparisons with alternative approaches.
1 citations
References
More filters
[...]
TL;DR: In this article, the authors explore three aspects of the problem in the context of finding small faces: the role of scale invariance, image resolution, and contextual reasoning, and train separate detectors for different scales.
Abstract: Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the context of finding small faces: the role of scale invariance, image resolution, and contextual reasoning. While most recognition approaches aim to be scale-invariant, the cues for recognizing a 3px tall face are fundamentally different than those for recognizing a 300px tall face. We take a different approach and train separate detectors for different scales. To maintain efficiency, detectors are trained in a multi-task fashion: they make use of features extracted from multiple layers of single (deep) feature hierarchy. While training detectors for large objects is straightforward, the crucial challenge remains training detectors for small objects. We show that context is crucial, and define templates that make use of massively-large receptive fields (where 99% of the template extends beyond the object of interest). Finally, we explore the role of scale in pre-trained deep networks, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges. We demonstrate state-of-the-art results on massively-benchmarked face datasets (FDDB and WIDER FACE). In particular, when compared to prior art on WIDER FACE, our results reduce error by a factor of 2 (our models produce an AP of 82% while prior art ranges from 29-64%).
579 citations
Posted Content•
[...]
TL;DR: The role of scale in pre-trained deep networks is explored, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges and demonstrating state-of-the-art results on massively-benchmarked face datasets.
Abstract: Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the context of finding small faces: the role of scale invariance, image resolution, and contextual reasoning. While most recognition approaches aim to be scale-invariant, the cues for recognizing a 3px tall face are fundamentally different than those for recognizing a 300px tall face. We take a different approach and train separate detectors for different scales. To maintain efficiency, detectors are trained in a multi-task fashion: they make use of features extracted from multiple layers of single (deep) feature hierarchy. While training detectors for large objects is straightforward, the crucial challenge remains training detectors for small objects. We show that context is crucial, and define templates that make use of massively-large receptive fields (where 99% of the template extends beyond the object of interest). Finally, we explore the role of scale in pre-trained deep networks, providing ways to extrapolate networks tuned for limited scales to rather extreme ranges. We demonstrate state-of-the-art results on massively-benchmarked face datasets (FDDB and WIDER FACE). In particular, when compared to prior art on WIDER FACE, our results reduce error by a factor of 2 (our models produce an AP of 82% while prior art ranges from 29-64%).
518 citations
"Triplet Transform Learning for Auto..." refers methods in this paper
...[9] which uses TinyFace detector [10] to detect faces....
[...]
TL;DR: A methodology for online learning of square sparsifying transforms is developed and the proposed transform learning algorithms are shown to have a much lower computational cost than online synthesis dictionary learning.
Abstract: Techniques exploiting the sparsity of signals in a transform domain or dictionary have been popular in signal processing. Adaptive synthesis dictionaries have been shown to be useful in applications such as signal denoising, and medical image reconstruction. More recently, the learning of sparsifying transforms for data has received interest. The sparsifying transform model allows for cheap and exact computations. In this paper, we develop a methodology for online learning of square sparsifying transforms. Such online learning can be particularly useful when dealing with big data, and for signal processing applications such as real-time sparse representation and denoising. The proposed transform learning algorithms are shown to have a much lower computational cost than online synthesis dictionary learning. In practice, the sequential learning of a sparsifying transform typically converges faster than batch mode transform learning. Preliminary experiments show the usefulness of the proposed schemes for sparse representation, and denoising.
95 citations
"Triplet Transform Learning for Auto..." refers methods in this paper
...Proposed Triplet Transform Learning (TTL) incorporates the triplet loss in the otherwise unsupervised transform learning model....
[...]
...This research proposes a novel primate recognition framework, built on the proposed Triplet Transform Learning (TTL) model....
[...]
...One such method is Transform Learning [11], which generates meaningful sparse representations from limited training images....
[...]
...The proposed model, termed as Triplet Transform Learning (TTL), utilizes transform learning to extract effective embeddings from existing feature extraction techniques, while increasing the interclass separability and reducing the intra-class distance....
[...]
...Index Terms— Animal Biometrics, Transform Learning, Triplet Loss, Primate Face Recognition...
[...]
12 Sep 2016
TL;DR: This paper builds on convolutional neural networks, which lead to significantly superior results compared with previous state-of-the-art on hand-crafted recognition pipelines, and shows how to further increase discrimination abilities of CNN activations by the Log-Euclidean framework on top of bilinear pooling.
Abstract: In this paper, we investigate how to predict attributes of chimpanzees such as identity, age, age group, and gender. We build on convolutional neural networks, which lead to significantly superior results compared with previous state-of-the-art on hand-crafted recognition pipelines. In addition, we show how to further increase discrimination abilities of CNN activations by the Log-Euclidean framework on top of bilinear pooling. We finally introduce two curated datasets consisting of chimpanzee faces with detailed meta-information to stimulate further research. Our results can serve as the foundation for automated large-scale animal monitoring and analysis.
78 citations
"Triplet Transform Learning for Auto..." refers background or methods in this paper
...Sample cropped faces of three identities from the primate dataset [7, 9]....
[...]
...Experimental evaluation on the primate database [7, 9] illustrates the effectiveness of the proposed framework....
[...]
...Experiments have been performed on the primate dataset [7, 9] containing 927 images of 80 primates belonging to Rhesus Macaque (Macaca mulatta), Chimpanzees (Pan troglodytes) and Western Gorillas (Gorilla gorilla)....
[...]
...[7] proposed an approach which uses Convolutional Neural Networks (Log Euclidean) for primate face recognition....
[...]
17 Feb 2017
TL;DR: LemurFaceID is a computer-assisted facial recognition system that can be used to identify individual lemurs based on photographs of wild individuals with a relatively high degree of accuracy and suggests that human facial recognition techniques can be modified for identification of individual leMursbased on variation in facial patterns.
Abstract: Long-term research of known individuals is critical for understanding the demographic and evolutionary processes that influence natural populations. Current methods for individual identification of many animals include capture and tagging techniques and/or researcher knowledge of natural variation in individual phenotypes. These methods can be costly, time-consuming, and may be impractical for larger-scale, population-level studies. Accordingly, for many animal lineages, long-term research projects are often limited to only a few taxa. Lemurs, a mammalian lineage endemic to Madagascar, are no exception. Long-term data needed to address evolutionary questions are lacking for many species. This is, at least in part, due to difficulties collecting consistent data on known individuals over long periods of time. Here, we present a new method for individual identification of lemurs (LemurFaceID). LemurFaceID is a computer-assisted facial recognition system that can be used to identify individual lemurs based on photographs. LemurFaceID was developed using patch-wise Multiscale Local Binary Pattern features and modified facial image normalization techniques to reduce the effects of facial hair and variation in ambient lighting on identification. We trained and tested our system using images from wild red-bellied lemurs (Eulemur rubriventer) collected in Ranomafana National Park, Madagascar. Across 100 trials, with different partitions of training and test sets, we demonstrate that the LemurFaceID can achieve 98.7% ± 1.81% accuracy (using 2-query image fusion) in correctly identifying individual lemurs. Our results suggest that human facial recognition techniques can be modified for identification of individual lemurs based on variation in facial patterns. LemurFaceID was able to identify individual lemurs based on photographs of wild individuals with a relatively high degree of accuracy. This technology would remove many limitations of traditional methods for individual identification. Once optimized, our system can facilitate long-term research of known individuals by providing a rapid, cost-effective, and accurate method for individual identification.
68 citations
"Triplet Transform Learning for Auto..." refers methods in this paper
...[6] developed a LemurFaceID system for lemurs which utilizes Multiscale Local Binary Pattern (MLBP) features and facial image normalization techniques....
[...]