Statistical learning applied to computer-assisted fish age and growth estimation from otolith images

Fablet, Ronan

doi:10.1016/j.fishres.2006.07.013

Cited by 13 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Icelandic plaice and Bay of Biscay anchovy), and could potentially deliver a cost benefit. Although Eastern Channel plaice exhibit high-contrast growth marks, the results suffer from high relative bias (year groups 5 to 6+), and the average percent error found by AFISA is much poorer than that reported in previous studies published by Fablet and colleagues, which seems to suggest that some of these systems combine image-based and morphological information (Fablet 2006b).…”

Section: The Need For Further Workcontrasting

confidence: 59%

“…Machine learning is a paradigm that seems to deliver the best results in terms of performance for automatic ageing, and neural network and statistical frameworks are popular implemen tations. Approaches that use machine learning paradigms often derive features from spatial and frequency do main analysis of 1-D transect signals, sometimes combined with 2-D features extracted from the image (Robertson & Morison 1999, Fablet et al 2004, Fablet & Le Josse 2005, Fablet 2006a) and other measurements such as weight (Fablet 2006b, Bermejo 2007.…”

Section: -D Analysismentioning

confidence: 99%

“…The results from AFISA have been published in the form of an EU report only (Mahé 2009), although a subset of the work concerning Eastern Channel plaice feature widely in publications by Fablet and colleagues (Fablet 2005, 2006b, Fablet & Le Josse 2005. AFISA also analyse transect signals but employ a statistical framework and more complex pre-processing than do Robertson and colleagues (Morison et al 1998, Robertson & Morison 1999, 2001).…”

Section: The Need For Further Workmentioning

confidence: 99%

See 2 more Smart Citations

Digital imaging techniques in otolith data capture, analysis and interpretation

Fisher¹,

Hunter²

2018

Mar. Ecol. Prog. Ser.

View full text Add to dashboard Cite

Otoliths or ear-stones are hard, calcium carbonate structures located within the inner ear of bony fishes. Counts of rings and measurements of seasonal growth increments from otoliths are important metrics for assessment and management of fish stocks, and the preparation and microscopic analysis of otoliths forms an essential part of the routine work undertaken by fisheries scientists worldwide. Otolith analysis is a skilled task requiring accuracy and precision, but it is laborious, time-consuming to perform, and represents a significant cost to fisheries management. In the last 2 decades, several attempts to apply 'computer vision' (systems that perform high-level tasks and exhibit intelligent behaviour) in otolith analysis have been reported. Although considerable progress has been made and several prototype systems developed, laboratories have been reluctant to adopt image-based computer-assisted age and growth estimation (CAAGE) systems. This paper surveys applications of CAAGE, focusing on their utility for automated ageing using images of otolith macrostructure. A cost−benefit analysis of CAAGE of cod, plaice and anchovy shows that computer vision performs relatively poorly compared with morphometric techniques. However, there is evidence that information from visual features can boost the performance of morphometric CAAGE, and further work is needed to develop effective frameworks for this integrated approach. The cost benefit of these systems might be attractive to smaller laboratories that are already using age−length keys derived from otolith morphometrics for management of smaller artisanal fisheries. KEY WORDS: Otolith • Computer-assisted age and growth estimation • CAAGE • Image analysis • Computational model Contribution to the Theme Section 'Innovative use of sclerochronology in marine resource management'

show abstract

Section: The Need For Further Workcontrasting

confidence: 59%

Section: -D Analysismentioning

confidence: 99%

Section: The Need For Further Workmentioning

confidence: 99%

See 1 more Smart Citation

Digital imaging techniques in otolith data capture, analysis and interpretation

Fisher¹,

Hunter²

2018

Mar. Ecol. Prog. Ser.

View full text Add to dashboard Cite

show abstract

“…Apart from routine aging, the proposed approach can be used in a number of different ways to assist the experts in the acquisition of age and growth data. As an illustration, one could use it as a low cost solution for a second reading of the samples to detect unrealistic interpretation or to evaluate confidence measures of the age estimation (Fablet 2005). Such measures are of great interest for assessment models (Reeves 2003).…”

mentioning

confidence: 99%

Semi-local extraction of ring structures in images of biological hard tissues: application to the Bayesian interpretation of fish otoliths for age and growth estimation

Fablet¹

2006

Can. J. Fish. Aquat. Sci.

Self Cite

View full text Add to dashboard Cite

This paper deals with the analysis of images of biological tissue that involves ring structures, such as tree trunks, bivalve seashells, or fish otoliths, with a view to automating the acquisition of age and growth data. A bottom-up template-based scheme extracts meaningful ridge and valley curve data using growth-adapted time-frequency filtering. Age and growth estimation is then stated as the Bayesian selection of a subset of ring curves, which combines a measure of curve significativity and an a priori statistical growth model. Experiments on real samples demonstrate the efficiency of the proposed data extraction stage. Our Bayesian framework is shown to significantly outperform previous methods for the interpretation of a data set of 200 plaice otoliths and compares favorably with interexpert agreement rates (88% of agreement to expert interpretations). Problem statement and related workAge and growth data provide key information for a broad range of scientific issues: for instance, the computation of daily temperature series for paleoclimatology from the analysis of daily increments 30 on the shell of sea scallops (Chauvaud 2004), the determination of age-length keys from the interpretation of fish otoliths for marine stock assessments (Panfili et al. 2003), the analysis of fish otolith growth patterns for marine ecology (Hare and Cowen 1997;Panfili et al. 2003) or tree-ring dating for archeology (Baillie 1982). All of these applications initially rely on the interpretation of growth rings observed on biological materials such as tree trunks, corals, shells of seashells, fish otoliths, fish scales, 35 which will be subsequently referred as biological hard tissues (Fig. 1). The presence of concentric ring structures is due to the variations in chemistry during the accretionary formation of these structures.The deposit of the rings is often associated with a biological periodicity (either seasonal or daily, depending on the species and the tissue). Counting growth rings then leads to an estimation of the age of the analyzed tissue, whereas growth increments can be estimated from the distance between successive 40 rings (Fig. 2), however, not all the observed ring structures are relevant for aging (Campana 2001).The previously mentioned biological applications require large collections of age and growth data for a consistent analysis. The acquisition of this data is generally performed by expert readers (typically, for marine stock assessment issues, several thousands of fish otoliths per year). The development of digital imaging systems and computer-aided tools brings new solutions to this field, (Small and 45 Hirschhorn 1987;Guay 1997;Morison et al. 1998). Our work focuses on the automation of age and growth estimation from the analysis of ring structures within the images of biological hard tissues. As detailed below, the key issues lie in the use of growth information to design a ring extraction framework that takes into account growth non-linearity (Fig. 2.b), and to discriminate actual growth rings...

show abstract

“…a priori growth information: P (e C ) = P (g eC is relevant). This probabilistic model is learned from training samples using kernel logistic regression as presented in [3].…”

Section: Image Interpretation For Age and Growth Estimationmentioning

confidence: 99%

Extraction and interpretation of ring structures in images of biological hard tissues: application to fish age and growth estimation

Fablet

2005

IEEE International Conference on Image Processing 2005

View full text Add to dashboard Cite

This paper presents a general framework for the automated estimation of age and growth from images of biological materials depicting concentric ring-like structures such as tree trunks, corals, bivalve seashells, fish scales or otoliths. This interpretation task can be seen as a ring segmentation issue, where growth rings are associated to image ridge and valley structures. This is stated as the Bayesian selection of a subset of partial ring curves extracted using a semi-local template-based growth-adapted scheme. The application to fish otolith interpretation provides a consistent and convincing validation of the proposed framework.

show abstract

Statistical learning applied to computer-assisted fish age and growth estimation from otolith images

Cited by 13 publications

References 9 publications

Digital imaging techniques in otolith data capture, analysis and interpretation

Digital imaging techniques in otolith data capture, analysis and interpretation

Semi-local extraction of ring structures in images of biological hard tissues: application to the Bayesian interpretation of fish otoliths for age and growth estimation

Extraction and interpretation of ring structures in images of biological hard tissues: application to fish age and growth estimation

Contact Info

Product

Resources

About