Otolith Images Research Articles

A guide to the otoliths of Southern Ocean lanternfishes (Myctophidae)

In the Southern Ocean, myctophids (family Myctophidae) are speciose, dominate the mesopelagic fish biomass, and are important in the diets of many fishes, squids, seabirds, and marine mammals. Consequently, they play a key role in carbon export and energy transfer from primary consumers to top predators. However, they are delicate and rarely found intact in predator stomachs, which makes them difficult to identify to species. Fortunately, their otoliths (sagittae) are mostly distinctive and therefore useful for species identification. Previous studies describing Southern Ocean myctophid otoliths were often limited by small sample sizes or focused on only a few species. To facilitate myctophid identifications in diet studies, we provide scanning electron microscope images of otoliths with brief descriptions for 37 species of Southern Ocean myctophids. The identities of problematic taxa were confirmed with DNA. Most species were found to have distinctive otoliths, which can be used to identify them to the species level. Large Gymnoscopelus piabilis otoliths comprised two types, which may represent different species. In addition, allometric equations are provided for 32 species to enable back calculation of fish size.

Fish age reading using deep learning methods for object-detection and segmentation

Abstract Determination of individual age is one essential step in the accurate assessment of fish stocks. In non-tropical environments, the manual count of ring-like growth patterns in fish otoliths (ear stones) is the standard method. It relies on visual means and individual judgment and thus is subject to bias and interpretation errors. The use of automated pattern recognition based on machine learning may help to overcome this problem. Here, we employ two deep learning methods based on Convolutional Neural Networks (CNNs). The first approach utilizes the Mask R-CNN algorithm to perform object detection on the major otolith reading axes. The second approach employs the U-Net architecture to perform semantic segmentation on the otolith image in order to segregate the regions of interest. For both methods, we applied a simple postprocessing to count the rings on the output masks returned, which corresponds to the age prediction. Multiple benchmark tests indicate the promising performance of our implemented approaches, comparable to recently published methods based on classical image processing and traditional CNN implementation. Furthermore, our algorithms showed higher robustness compared to the existing methods, while also having the capacity to extrapolate missing age groups and to adapt to a new domain or data source.

FishAgePredictioNet: A multi-stage fish age prediction framework based on segmentation, deep convolution network, and Gaussian process regression with otolith images

Fish ageing is a vital component of fisheries management as it enables the evaluation of fish population status and supports the development of sustainable management strategies. However, traditional methods of age determination through otolith analysis by experts are resource-intensive and time-consuming. Therefore, there is a growing demand for more cost-effective and automated techniques to accurately determine fish age. In accordance with this purpose, we proposed a multistage framework for fish age prediction using otolith images. First, otoliths in the images were detected using the Faster Region-based Convolutional Neural Networks (RCNN) model, which includes 8 convolution layers, and the detected otoliths were clipped. Subsequently, using a pre-trained neural network based on the transfer learning approach, deep features were extracted separately from the right and left otolith images, and all the obtained features were combined. Finally, these combined features are given as input to the Gaussian process regression model. To evaluate the performance of the proposed architecture, 4109 images of right and left otoliths belonging to Greenland halibut (flatfish, Reinhardtius hippoglossoides) were used. The proposed architecture produced 1.83 MSE, 0.98 R-squared, 1.35 RMSE, and 10.29 MAPE scores in the experimental studies. As a result, the proposed model achieved superior performance compared with previous studies. Our findings show that our FishAgePredictioNet system could help experts predict fish age based on otolith images.

Using teacher-student neural networks based on knowledge distillation to detect anomalous samples in the otolith images

Otoliths are small calcium carbonate structures found in the inner ear of fish and they, as one of important information carriers, are applied in diverse ecological fields. Otoliths are usually photographed and used to explore many unsolved biological and ecological questions. However, many anomalies may occur in the large volume of otolith image data due to natural or artificial consequences, which brings a huge bias to the aimed study and even misleading results. In this study, we first propose a specific definition of otolith anomalies and provide a dataset of otolith anomalies with Electrona carlsbergi, one of the most abundant species of lanternfishes, as the study subject. We modify a multiresolution knowledge distillation neural network model, the state-of-the-art anomaly detection model to a multiresolution knowledge distillation network model with asymmetric inputs, which uses grayscale maps to align the features of color maps in the feature space, to help improve otolith anomalies detection. Our fine-tuned anomaly detection network obtains a better anomaly identification performance with a Receiving Operating Characteristic Area Under the Curve value of 0.9843. Our result shown that multiresolution knowledge distillation networks can efficiently identify abnormal otolith image sample, which is of great importance for conducting otolith-based science.

Annotating otoliths with a deep generative model

Abstract Otoliths are a central information source for fish ecology and stock management, conveying important data about age and other life history for individual fish. Traditionally, interpretation of otoliths has required skilled expert readers, but recently deep learning classification and regression models have been trained to extract fish age from images of otoliths from a variety of species. Despite high accuracy in many cases, the adoption of such models in fisheries management has been slow. One reason may be that the underlying mechanisms the model uses to derive its results from the data are opaque, and this lack of legibility makes it challenging to build sufficient trust in the results. Here, we implement a deep learning model that instead of age predicts the location of annotation marks for each of the annuli. This allows an expert to evaluate the model’s performance in detail. The quality of the annotations was judged by a panel of four expert otolith readers in a double-blinded randomized survey. Using a scale from 1 to 5, the generated marks received an average quality score of 4.22, whereas expert annotations received an average score of 4.33. By counting the marks to determine fish age, we obtained an agreement between expert and model annotations of 64% on our test set, which running the model stochastically increased to 69%. Stochastic sampling yields further benefits, including an explicit measure of the model’s uncertainty, the post hoc likelihood of the different age classes for each otolith, and a set of alternative annotation sequences that highlight the structure of the annuli.

Age interpretation of cod otoliths using deep learning

Fish age estimation plays a crucial role in stock management and provides valuable information for biological studies. Fish age is typically estimated by experts that manually count annual increments in otoliths. This process is prone to age reader bias, which makes comparisons between readers and labs challenging, and requires considerable time and resources. In this study, we developed a machine learning framework for fish age prediction using 5150 images of otoliths from Barents Sea Atlantic cod (Gadus morhua) collected between 2012 and 2018. In contrast to previous studies that utilise models trained on otolith sections, we used images of broken otoliths that require no processing prior to imaging, and hence, could potentially facilitate at-sea age estimation. We trained convolutional neural networks (CNNs) based on two modern architectures (EfficientNetV1 and EfficientNetV2), which vary in model size (number of model parameters), and compared performance. Model average accuracy was 72.7% and mean-squared-error was 0.284 when compared with the human-read ages. The models' accuracy for one- and two-year-old individuals was over 90% and no systematic bias in the age predictions across age groups was detected. The best models were EfficientNet B4 and EfficientNet B6 using images taken with low exposure times. A maximum accuracy of 78.6% was achieved using an ensemble consisting of six models. Model predictions were also strongly correlated, limiting the utility of building large ensembles Model performance was compared to the results of an internal workshop where 100 independent images of broken otoliths were aged by a group of experts. Variations in percentage agreement between age classes showed a similar pattern (decreasing with age) in both CNN-based predictions and age estimates made by the expert group. While CNN-based percentage agreement was often lower than the expert estimates, it remained within or close to the range of percentage agreement observed across all readers. Our results demonstrate the potential of deep learning techniques for extracting age estimates from otolith images. When developing frameworks for age estimation using machine learning, we recommend EfficientNet B4 models are used as they are quicker to train than larger models and perform well. Ensemble approaches are also recommended if sufficient computational resources are available, as they can provide increased accuracy and lower variance of the predictions.

Otolith characterization and integrative species identification of adult mesopelagic fishes from the western North Atlantic Ocean

Fish diversity and ecology in the ocean’s mesopelagic zone are understudied compared to other marine regions despite growing interest in harvesting these potential resources. Otoliths can provide a wealth of taxonomic and life history information about fish, which can help fill these knowledge gaps; however, there has been relatively little research to date on the otoliths of mesopelagic species. Here, a species-specific image library was assembled of sagittal otoliths from 70 mesopelagic fishes belonging to 29 families collected in the western North Atlantic Ocean. Images of adult sagittal otoliths from 12 species were documented and photographed for the first time. The fish were identified to species with a combination of morphological characters and DNA barcoding. Regressions between otolith size and fish length are presented for the six species with the largest sample sizes in this study. This otolith image library, coupled with otolith-length and width to fish-length relationships, can be used for prey identification and back-calculation of fish size, making it a valuable tool for studies relating to food webs in the important yet poorly understood mesopelagic zone. In addition, the 44 fish barcodes generated in this study highlight the benefit of using an integrative taxonomic approach to studies of this nature, as well as add to existing public databases that enable cryptic species and metabarcoding analyses of mesopelagic species.

Age Determination of the Azov Anchovy Engraulis encrasicolus maeoticus (Engraulidae) Based on the Otolith Image Analysis

To specify the age determination of the Azov anchovy Engraulis encrasicolus maeoticus, the length of otoliths of the age 0+ fish and the radii of annual rings in the otoliths of individuals of different age groups have been analysed. The otoliths of 380 fish caught in the Sea of Azov in October–November 2018 and off the northwestern coast of the Caucasus in February 2019 have been analyzed. The ImageJ software has been used for measuring the maximum otolith length and plotting the reflected light intensity profiles along the length of the otolith transect. In the fingerlings (0+) with an average total length of 70.9 ± 6.7 mm, in October–November, the otolith radius averaged 0.95 ± 0.08 mm, while in February, with an average 66.6 ± 10.6 mm, it was 0.86 ± 0.15 mm. In the smallest fish (48–55 mm), the distance from the core of the otolith to the edge of the white opaque zone varied from 0.54 to 0.72 mm (on average, 0.63 ± 0.04 mm). According to the averaged data, the radii to the center of the dark hyaline zone of otoliths for different age groups of anchovy are: R1, 0.94 ± 0.09; R2, 1.23 ± 0.08; and R3, 1.40 ± 0.07 mm. The present study is aimed at developing automatic methods for determining the age of fish from light intensity profile peaks on otolith images.

Age prediction by deep learning applied to Greenland halibut (Reinhardtius hippoglossoides) otolith images.

Otoliths (ear-stones) in the inner ears of vertebrates containing visible year zones are used extensively to determine fish age. Analysis of otoliths is a time-consuming and difficult task that requires the education of human experts. Human age estimates are inconsistent, as several readings by the same human expert might result in different ages assigned to the same otolith, in addition to an inherent bias between readers. To improve efficiency and resolve inconsistent results in the age reading from otolith images by human experts, an automated procedure based on convolutional neural networks (CNNs), a class of deep learning models suitable for image processing, is investigated. We applied CNNs that perform image regression to estimate the age of Greenland halibut (Reinhardtius hippoglossoides) with good results for individual ages as well as the overall age distribution, with an average CV of about 10% relative to the read ages by experts. In addition, the density distribution of predicted ages resembles the density distribution of the ground truth. By using k*l-fold cross-validation, we test all available samples, and we show that the results are rather sensitive to the choice of test set. Finally, we apply explanation techniques to analyze the decision process of deep learning models. In particular, we produce heatmaps indicating which input features that are the most important in the computation of predicted age.

DeepOtolith v1.0: An Open-Source AI Platform for Automating Fish Age Reading from Otolith or Scale Images

Every year, marine scientists around the world read thousands of otolith or scale images to determine the age structure of commercial fish stocks. This knowledge is important for fisheries and conservation management. However, the age-reading procedure is time-consuming and costly to perform due to the specialized expertise and labor needed to identify annual growth zones in otoliths. Effective automated systems are needed to increase throughput and reduce cost. DeepOtolith is an open-source artificial intelligence (AI) platform that addresses this issue by providing a web system with a simple interface that automatically estimates fish age by combining otolith images with convolutional neural networks (CNNs), a class of deep neural networks that has been a dominant method in computer vision tasks. Users can upload otolith image data for selective fish species, and the platform returns age estimates. The estimates of multiple images can be exported to conduct conclusions or further age-related research. DeepOtolith currently contains classifiers/regressors for three fish species; however, more species will be included as related work on ageing will be tested and published soon. Herein, the architecture and functionality of the platform are presented. Current limitations and future directions are also discussed. Overall, DeepOtolith should be considered as the first step towards building a community of marine ecologists, machine learning experts, and stakeholders that will collaborate to support the conservation of fishery resources.

Automatic Fish Age Determination across Different Otolith Image Labs Using Domain Adaptation

The age determination of fish is fundamental to marine resource management. This task is commonly done by analysis of otoliths performed manually by human experts. Otolith images from Greenland halibut acquired by the Institute of Marine Research (Norway) were recently used to train a convolutional neural network (CNN) for automatically predicting fish age, opening the way for requiring less human effort and availability of expertise by means of deep learning (DL). In this study, we demonstrate that applying a CNN model trained on images from one lab (in Norway) does not lead to a suitable performance when predicting fish ages from otolith images from another lab (in Iceland) for the same species. This is due to a problem known as dataset shift, where the source data, i.e., the dataset the model was trained on have different characteristics from the dataset at test stage, here denoted as target data. We further demonstrate that we can handle this problem by using domain adaptation, such that an existing model trained in the source domain is adapted to perform well in the target domain, without requiring extra annotation effort. We investigate four different approaches: (i) simple adaptation via image standardization, (ii) adversarial generative adaptation, (iii) adversarial discriminative adaptation and (iv) self-supervised adaptation. The results show that the performance varies substantially between the methods, with adversarial discriminative and self-supervised adaptations being the best approaches. Without using a domain adaptation approach, the root mean squared error (RMSE) and coefficient of variation (CV) on the Icelandic dataset are as high as 5.12 years and 28.6%, respectively, whereas by using the self-supervised domain adaptation, the RMSE and CV are reduced to 1.94 years and 11.1%. We conclude that careful consideration must be given before DL-based predictors are applied to perform large scale inference. Despite that, domain adaptation is a promising solution for handling problems of dataset shift across image labs.

Relationship between fish size and otolith size of four deep-sea fishes from the Western Bay of Bengal, India

The present study provides the otolith morphology and morphometric relationships with fish size of four deep-sea fishes ( Parascombrops pellucidus Alcock, 1889, Alepocephalus blanfordii Alcock, 1892, Lamprogrammus niger Alcock, 1891, Pterygotrigla hemisticta (Temminck & Schlegel, 1843)) collected from western Bay of Bengal during March 2020. Among these, the equations were derived for the first time for three species ( P. pellucidus , A. blanfordii , L. niger ). Sampling was done as a part of deep-sea exploratory survey of FORV Sagar Sampada along the deeper shelf regions of the Bay of Bengal at a depth range of 200 – 1000 m using high-speed demersal trawl (HSDT-CV). The numerical relations established using regression between fish size (TL) and various otolith morphometric measurements (otolith length (OL), otolith height (OH), otolith weight (OWe), otolith area (OA) and otolith perimeter (OP)) can be used to predict the prey size in food and feeding studies for studying the food web dynamics of less-studied deep-sea fishes. LWR of the otolith of selected species showed a negative allometric growth ( t- test, p < 0.5). The higher r 2 value ( > 0.70) obtained for the relationship between fish size (TL) and various otolith morphometric measurements indicates the robustness of the model. The representative images of otoliths of these fishes will be helpful to the taxonomists for the species confirmation and reconstruction of past species assemblages in the palaeontological studies.

Counting using deep learning regression gives value to ecological surveys

Many ecological studies rely on count data and involve manual counting of objects of interest, which is time-consuming and especially disadvantageous when time in the field or lab is limited. However, an increasing number of works uses digital imagery, which opens opportunities to automatise counting tasks. In this study, we use machine learning to automate counting objects of interest without the need to label individual objects. By leveraging already existing image-level annotations, this approach can also give value to historical data that were collected and annotated over longer time series (typical for many ecological studies), without the aim of deep learning applications. We demonstrate deep learning regression on two fundamentally different counting tasks: (i) daily growth rings from microscopic images of fish otolith (i.e., hearing stone) and (ii) hauled out seals from highly variable aerial imagery. In the otolith images, our deep learning-based regressor yields an RMSE of 3.40 day-rings and an R^2 of 0.92. Initial performance in the seal images is lower (RMSE of 23.46 seals and R^2 of 0.72), which can be attributed to a lack of images with a high number of seals in the initial training set, compared to the test set. We then show how to improve performance substantially (RMSE of 19.03 seals and R^2 of 0.77) by carefully selecting and relabelling just 100 additional training images based on initial model prediction discrepancy. The regression-based approach used here returns accurate counts (R^2 of 0.92 and 0.77 for the rings and seals, respectively), directly usable in ecological research.

Automating fish age estimation combining otolith images and deep learning: The role of multitask learning

Knowledge on the age of fish is vital for assessing the status of fish stocks and proposing management actions to ensure their sustainability. Prevalent methods of fish ageing are based on the readings of otolith images by experts, a process that is often time-consuming and costly. This suggests the need for automatic and cost-effective approaches. Herein, we investigate the feasibility of using deep learning to provide an automatic estimation of fish age from otolith images through a convolutional neural network designed for image analysis. On top of this network, we propose an enhanced - with multitask learning - network to better estimate fish age by introducing as an auxiliary training task the prediction of fish length from otolith images. The proposed approach is applied on a collection of 5027 otolith images of red mullet (Mullus barbatus), considering fish age estimation as a multi-class classification task with six age groups (Age-0, Age-1, Age-2, Age-3, Age-4, Age-5+). Results showed that the network without multitask learning predicted fish age correctly by 64.4 %, attaining high performance for younger age groups (Age-0 and Age-1, F1 score > 0.8) and moderate performance for older age groups (Age-2 to Age-5+, F1 score: 0.50−0.54). The network with multitask learning increased correctness in age prediction reaching 69.2 % and proved efficient to leverage its predictive performance for older age groups (Age-2 to Age-5+, F1 score: 0.57−0.64). Our findings suggest that deep learning has the potential to support the automation of fish age reading, though further research is required to build an operational tool useful in routine fish aging protocols for age reading experts.

Fine-scale variability in otolith chemistry: Application to the life history analysis of Pacific cod (Gadus macrocephalus) in the Yellow Sea

The Yellow Sea is the southwestern limit of the distribution of Pacific cod (Gadus macrocephalus), a typical cold water and commercially important fish in the North Pacific. The catch of Pacific cod in the Yellow Sea has increased gradually in recent years, and has received substantial attention. To explore the use of otolith chemistry in the characterization of different spawning grounds and crucial life history events, a total of 60 specimens of Pacific cod were obtained from October 2016 to August 2017. The contents of barium (Ba) and strontium (Sr) in otoliths from the core to the edge along the ventral side were determined using laser ablation-inductively coupled plasma-mass spectrometry. Based on hierarchical cluster analysis (HCA), the specimens were assigned to two groups based on the ratio of Ba:Ca at the core. The various patterns of core-to-edge Ba:Ca inferred using a linear mixed-effect (LMM) model suggested differences in the spawning ground environments for Pacific cod in the Yellow Sea, and step changes found in the Sr:Ca ratio, and a corresponding check observed in otolith images suggest that the settlement of Pacific cod occurred approximately 80–120 days after hatching. The nature of the data prevents firm conclusions being drawn from the data available at present, but the significant differences in certain elements among individuals and the association with crucial life history events in Pacific cod are noteworthy.

Stock separation of the shallow-water hake Merluccius capensis in the Benguela ecosystem using otolith shape analysis

The fishing industry is an important economic sector in Namibia and South Africa, with the shallow-water hake Merluccius capensis being an important target species. Recent genetic studies of M. capensis found two stocks in the Benguela Current Large Marine Ecosystem, one in the north (17–29° S) and one in the south (29–36° S), and a proposed mixed stock in the Orange River area (around 29° S). The present study investigated the use of otolith shape analysis for purposes of stock-structure analysis of M. capensis. Merluccius capensis otolith samples were collected during demersal-trawl surveys along the Benguela, for the years 1992, 2004 and 2005. Different years were selected to investigate temporal stability in otolith shape in the northern Benguela. A total of 1 628 otolith images were analysed using the shapeR library in R. Otolith shape was analysed using wavelet transformation, and ANOVA-like permutation tests indicated no significant differences between the northern (17°31′–25°29′ S) and central (25°30′–29°05′ S) Benguela for all years but showed significant differences between the northern and southern (29°05′–35°50′ S) Benguela. This study therefore demonstrated that otolith shape could be used for stock discrimination of M. capensis. It confirmed one stock of M. capensis in the northern and central Benguela and another in the southern Benguela, which supports the current, separate management approach for this species. It also showed some differences in otolith shape from the 1990s to the 2000s, which could be explained by increased movement of the southern Benguela stock to the northern Benguela and increased hybridisation in the later years.

The Size and The Shape of Sagittal Otolith of Redtail Scad, <i>Decapterus kurroides</i> Blekeer 1855 from Kema Bay, North Minahasa Regency, North Sulawesi, Indonesia

This study aimed to examine the difference in the otolith size and otolith shape of redtail scad Decapterus kurrodes between sex in North Sulawesi. The otoliths of D. kurroides were studied for sagitta otolith pair samples of 34 juveniles, 58 females and 75 males from Kema Bay. These pairs sagitta otolith images were interpreted using ImageJ tool to describe the otolith size (length, width, perimeter, and area), then we calculated the shape index (form factor, roundness, circularity, rectangularity, ellipticity and aspect ratio or length-width ratio). No significant difference was found in otolith length between left and right otoliths of juveniles of D. kurroides or called symmetrical but significant differences or asymmetrical were found in all sample, females and males. The regressions of total length against otolith sizes (otolith lengt, otolith width otolith perimeter and otolith area of D. kurroides follow a power function. The growth patterns showed dominant allometric growth in total length–otolith sizes relationships of D. kurroides from Kema Bay, Key Words: size, shape index, otolith, Decapterus kurroides, Kema Bay.

Otolith identification using a deep hierarchical classification model

The diet of seabirds can yield important insights into the status of economically and ecologically important fish. By analyzing the otoliths found in the birds’ droppings, researchers can observe which fish the birds eat in which abundances. However, identifying the species based on an otolith image is quite labor-intensive and requires particular expertise. In this work, we show that a deep convolutional neural network can identify six fish species with high accuracy. We show that this deep learning approach outperforms more traditional methods and is also more accessible to set up in practice. By exploiting the hierarchy in the species labels, we impose a structure on the prediction probabilities, leading to a remarkable improvement compared to a conventional artificial neural network. Importantly, we can attain good results using only a modest dataset, demonstrating that such approaches are feasible for small-scale and specialized projects.

Seeking the true time: Exploring otolith chemistry as an age-determination tool.

Fish otoliths' chronometric properties make them useful for age and growth rate estimation in fisheries management. For the Eastern Baltic Sea cod stock (Gadus morhua), unclear seasonal growth zones in otoliths have resulted in unreliable age and growth information. Here, a new age estimation method based on seasonal patterns in trace elemental otolith incorporation was tested for the first time and compared with the traditional method of visually counting growth zones, using otoliths from the Baltic and North seas. Various trace elemental ratios, linked to fish metabolic activity (higher in summer) or external environment (migration to colder, deeper habitats with higher salinity in winter), were tested for age estimation based on assessing their seasonal variations in concentration. Mg:Ca and P:Ca, both proxies for growth and metabolic activity, showed greatest seasonality and therefore have the best potential to be used as chemical clocks. Otolith image readability was significantly lower in the Baltic than in the North Sea. The chemical (novel) method had an overall greater precision and percentage agreement among readers (11.2%, 74.0%) than the visual (traditional) method (23.1%, 51.0%). Visual readers generally selected more highly contrasting zones as annuli whereas the chemical readers identified brighter regions within the first two annuli and darker zones thereafter. Visual estimates produced significantly higher, more variable ages than did the chemical ones. Based on the analyses in our study, we suggest that otolith microchemistry is a promising alternative ageing method for fish populations difficult to age, such as the Eastern Baltic cod.

Explaining decisions of deep neural networks used for fish age prediction.

Age-reading of fish otoliths (ear stones) is important for the sustainable management of fish resources. However, the procedure is challenging and requires experienced readers to carefully examine annual growth zones. In a recent study, convolutional neural networks (CNNs) have been demonstrated to perform reasonably well on automatically predicting fish age from otolith images. In the present study, we carefully investigate the prediction rule learned by such neural networks to provide insight into the features that identify certain fish age ranges. For this purpose, a recent technique for visualizing and analyzing the predictions of the neural networks was applied to different versions of the otolith images. The results indicate that supplementary knowledge about the internal structure improves the results for the youngest age groups, compared to using only the contour shape attribute of the otolith. However, the contour shape and size attributes are, in general, sufficient for older age groups. In addition, within specific age ranges we find that the network tends to focus on particular areas of the otoliths and that the most discriminating factors seem to be related to the central part and the outer edge of the otolith. Explaining age predictions from otolith images as done in this study will hopefully help build confidence in the potential of deep learning algorithms for automatic age prediction, as well as improve the quality of the age estimation.