Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
5,015
result(s) for
"Fish Identification"
Sort by:
Guide to the manta & devil rays of the world
Manta and devil rays are some of the most intriguing creatures in the ocean. Driven forward by powerful beats of wing-like pectoral fins, these filter feeders search the waters for prey, their horn-like head fins giving rise to ancient mariners' tales of fearsome devilfish dragging boats into the ocean depths.
Book
Fishes
There are more than 33,000 species of living fishes, accounting for more than half of the extant vertebrate diversity on Earth. This unique and comprehensive reference showcases the basic anatomy and diversity of all 82 orders of fishes and more than 150 of the most commonly encountered families, focusing on their distinctive features. Accurate identification of each group, including its distinguishing characteristics, is supported with clear photographs of preserved specimens, primarily from the archives of the Marine Vertebrate Collection at Scripps Institution of Oceanography. This diagnostic information is supplemented by radiographs, additional illustrations of particularly diverse lineages, and key references and ecological information for each group. An ideal companion to primary ichthyology texts, Fishes: A Guide to Their Diversity gives a broad overview of fish morphology arranged in a modern classification system for students, fisheries scientists, marine biologists, vertebrate zoologists, and everyday naturalists. This survey of the most speciose group of vertebrates on Earth will expand the appreciation of and interest in the amazing diversity of fishes.
eBook
500 freshwater aquarium fish : a visual reference to the most popular species
\"This updated, comprehensive, full-color reference covers 500 of the most popular freshwater aquarium fish. It provides concise at-a-glance information on their behavior, diet and breeding along with guidance and recommendations on setting up a freshwater aquarium. Species include: Cichlids, Catfish, Cyprinids, Characoids, Loaches and suckers, Gouramis, Rainbow fish and blue-eyes, Livebearers, and others\"-- Provided by publisher.
Book
Underwater image enhancement: a comprehensive review, recent trends, challenges and applications
The mysteries of deep-sea ecosystems can be unlocked to reveal new sources, for developing medical drugs, food and energy resources, and products of renewable energy. Research in the area of underwater image processing has increased significantly in the last decade. This is primarily due to the dependence of human beings on the valuable resources existing underwater. Effective work of exploring the underwater environment is achievable by having excellent methods for underwater image enhancement. The work presented in this article highlights the survey of underwater image enhancement algorithms. This work presents an overview of various underwater image enhancement techniques and their broad classifications. The methods under each classification are briefly discussed. Underwater datasets required for performing experiments are summarized from the available literature. Attention is also drawn towards various evaluation metrics required for the quantitative assessment of underwater images and recent areas of application in the domain.
Journal Article
Parvalbumin: A Major Fish Allergen and a Forensically Relevant Marker
Parvalbumins (PVALBs) are low molecular weight calcium-binding proteins. In addition to their role in many biological processes, PVALBs play an important role in regulating Ca2+ switching in muscles with fast-twitch fibres in addition to their role in many biological processes. The PVALB gene family is divided into two gene types, alpha (α) and beta (β), with the β gene further divided into two gene types, beta1 (β1) and beta2 (β2), carrying traces of whole genome duplication. A large variety of commonly consumed fish species contain PVALB proteins which are known to cause fish allergies. More than 95% of all fish-induced food allergies are caused by PVALB proteins. The authentication of fish species has become increasingly important as the seafood industry continues to grow and the growth brings with it many cases of food fraud. Since the PVALB gene plays an important role in the initiation of allergic reactions, it has been used for decades to develop alternate assays for fish identification. A brief review of the significance of the fish PVALB genes is presented in this article, which covers evolutionary diversity, allergic properties, and potential use as a forensic marker.
Journal Article
SCSFish2025: a large dataset from South China sea for coral reef fish identification
Coral reefs are one of the most biodiverse ecosystems on Earth and are extremely important for marine ecosystems. However, coral reefs are rapidly degrading globally, and for this reason, in-situ online monitoring systems are being used to monitor coral reef ecosystems in real time. At the same time, artificial intelligence technology, particularly deep learning technology, is playing an increasingly important role in the study of coral reef ecology, especially in the automatic detection and identification of coral reef fish. However, deep learning is essentially a data-driven technique that relies on high-quality datasets for training, while existing fish identification datasets suffer from low resolution and inaccurate labeling, which limits the application of deep learning techniques to coral reef fish identification. To better utilize deep learning techniques for real-time automatic detection and identification of coral reef fish from the data collected by the in-situ online monitoring system, this paper proposes a high-resolution, fish species-rich, and well-labeled coral reef fish dataset SCSFish2025, which is the first publicly available coral reef fish dataset in the waters of China’s Nansha Islands. SCSFish2025 contains 11,956 high-resolution underwater surveillance images and over 120,000 bounding boxes covering 30 species of fish that have been manually labelled by experienced fish identification experts, with sub-category labels for blurring, occlusion, and altered pose. Furthermore, this paper establishes a benchmark for the dataset by analyzing the detection performance of deep learning object detection techniques on this dataset using four state-of-the-art or typical object detection models as baseline models. The best baseline model RT-DETRv2 achieves mAP@50 performance of 0.9960 and 0.7486 respectively on the five-fold cross-validation of the training set and the independent test set. The release of this dataset will help promote the development of AI technology in the study of automatic detection and identification of coral reef fish, and provide strong support for the study of marine biodiversity and ecosystems. The project code and dataset are available at
https://github.com/FudanZhengSYSU/SCSFish2025
.
Journal Article
DNA barcoding Australia's fish species
Two hundred and seven species of fish, mostly Australian marine fish, were sequenced (barcoded) for a 655 bp region of the mitochondrial cytochrome oxidase subunit I gene (cox1). Most species were represented by multiple specimens, and 754 sequences were generated. The GC content of the 143 species of teleosts was higher than the 61 species of sharks and rays (47.1% versus 42.2%), largely due to a higher GC content of codon position 3 in the former (41.1% versus 29.9%). Rays had higher GC than sharks (44.7% versus 41.0%), again largely due to higher GC in the 3rd codon position in the former (36.3% versus 26.8%). Average within-species, genus, family, order and class Kimura two parameter (K2P) distances were 0.39%, 9.93%, 15.46%, 22.18% and 23.27%, respectively. All species could be differentiated by their cox1 sequence, although single individuals of each of two species had haplotypes characteristic of a congener. Although DNA barcoding aims to develop species identification systems, some phylogenetic signal was apparent in the data. In the neighbour-joining tree for all 754 sequences, four major clusters were apparent: chimaerids, rays, sharks and teleosts. Species within genera invariably clustered, and generally so did genera within families. Three taxonomic groups-dogfishes of the genus Squalus, flatheads of the family Platycephalidae, and tunas of the genus Thunnus-were examined more closely. The clades revealed after bootstrapping generally corresponded well with expectations. Individuals from operational taxonomic units designated as Squalus species B through F formed individual clades, supporting morphological evidence for each of these being separate species. We conclude that cox1 sequencing, or 'barcoding', can be used to identify fish species.
Journal Article
Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data
Adult American eels (Anguilla rostrata) are vulnerable to hydropower turbine mortality during outmigration from growth habitat in inland waters to the ocean where they spawn. Imaging sonar is a reliable and proven technology for monitoring of fish passage and migration; however, there is no efficient automated method for eel detection. We designed a deep learning model for automated detection of adult American eels from sonar data. The method employs convolution neural network (CNN) to distinguish between 14 images of eels and non-eel objects. Prior to image classification with CNN, background subtraction and wavelet denoising were applied to enhance sonar images. The CNN model was first trained and tested on data obtained from a laboratory experiment, which yielded overall accuracies of >98% for image-based classification. Then, the model was trained and tested on field data that were obtained near the Iroquois Dam located on the St. Lawrence River; the accuracy achieved was commensurate with that of human experts.
Journal Article
DNA barcoding and cryptic diversity in fishes from the Ili River Valley in China, Xinjiang
The Ili River Valley, located in the northwest of China, serves as a vital repository for fish genetic resources. Its extensive water network and diverse climate have given rise to a unique fish composition and endemic species. In this study, we collected the cytochrome c oxidase subunit I (COI) sequences from 660 fish specimens in the Ili River Valley. The effectiveness of DNA barcoding in identifying fish species in the area was assessed by examining genetic distances, constructing phylogenetic trees, and performing ABGD (Automatic Barcode Gap Discovery) analyses, among other methods. In total, 20 species were identified, including one unidentified species (Silurus sp.). Except for Silurus asotus and Hypophthalmichthys molitrix (only one sample), the maximum intraspecific genetic distance among the remaining species was smaller than the minimum interspecific distance, which proves that the species exhibit obvious barcode gaps. In the Neighbor‐Joining trees, 20 species formed separate monophyletic branches. According to ABGD analysis, 660 sequences were categorized into 19 Operational Taxonomic Units, with Silurus sp. and S. asotus grouped into a single OTU. The Silurus in this study exhibits shared haplotypes and significant genetic divergence, suggesting the potential presence of cryptic species. Furthermore, the nucleotide diversity across all species fell below the threshold level, indicating that the local fish population is gradually declining. In conclusion, this study has demonstrated the effectiveness of DNA barcoding in identifying fish species in the Ili River Valley, providing valuable data to support the conservation of local fish resources. With a 95% success rate in identifying species, DNA barcoding based on the mitochondrial COI gene was validated in this study using genetic diversity, species delimitation, genetic distances, and unidentified species analysis. Simultaneously, we discovered that the Ili River Valley's fish species populations are drastically decreasing to the point where the area faces a major ecological risk.
Journal Article
Transferable Deep Learning Model for the Identification of Fish Species for Various Fishing Grounds
The digitization of catch information for the promotion of sustainable fisheries is gaining momentum globally. However, the manual measurement of fundamental catch information, such as species identification, length measurement, and fish count, is highly inconvenient, thus intensifying the call for its automation. Recently, image recognition systems based on convolutional neural networks (CNNs) have been extensively studied across diverse fields. Nevertheless, the deployment of CNNs for identifying fish species is difficult owing to the intricate nature of managing a plethora of fish species, which fluctuate based on season and locale, in addition to the scarcity of public datasets encompassing large catches. To overcome this issue, we designed a transferable pre-trained CNN model specifically for identifying fish species, which can be easily reused in various fishing grounds. Utilizing an extensive fish species photographic database from a Japanese museum, we developed a transferable fish identification (TFI) model employing strategies such as multiple pre-training, learning rate scheduling, multi-task learning, and metric learning. We further introduced two application methods, namely transfer learning and output layer masking, for the TFI model, validating its efficacy through rigorous experiments.
Journal Article