scholarly journals Sea Turtle Facial Recognition Using Map Graphs of Scales

2021 ◽  
Author(s):  
Karun K. Rao ◽  
Lars C. Grabow ◽  
Juan P. Munoz-Perez ◽  
Daniela Alarcon-Ruales ◽  
Ricardo B. R. Azevedo

Individual identification of sea turtles is important to study their biology and aide in conservation efforts. Traditional methods for identifying sea turtles that rely on physical or GPS tags can be expensive, and difficult to implement. Alternatively, the scale structure on the side of a turtle's head has been shown to be specific to the individual and stable over its lifetime, and therefore can be used as the individual's "fingerprint". Here we propose a novel facial recognition method where an image of a sea turtle is converted into a graph (network) with nodes representing scales, and edges connecting two scales that share a border. The topology of the graph is used to differentiate species. We additionally develop a robust metric to compare turtles based on a correspondence between nodes generated by a coherent point drift algorithm and computing a graph edit distance to identify individual turtles with over 94% accuracy. By representing the special and topological features of sea turtle scales as a graph, we perform more accurate individual identification which is robust under different imaging conditions and may be adapted for a wider number of species.

Author(s):  
Wan Nural Jawahir Hj Wan Yussof ◽  
Nurfarahim Shaharudin ◽  
Muhammad Suzuri Hitam ◽  
Ezmahamrul Afreen Awalludin ◽  
Mohd Uzair Rusli ◽  
...  

Up to now, identification of sea turtle species mainly for tracking the population usually relied on flipper tags or through other physical markers. However, this approach is not practical due to the missing tags over some period. Due to this matter, we propose a photo identification system of the individual sea turtle based on the convolutional neural network (CNN) using a pre-trained AlexNet CNN and error-correcting output codes (ECOC) SVM. Experiments were performed on 300 images obtained from Biodiversity Research Center, Academia Sinica, Taiwan. Using Alexnet and ECOC SVM, the overall accuracy achieved is 62.9%. The results indicate that features obtained from the CNN are capable of identifying photo of sea turtles.


2021 ◽  
Author(s):  
Qiushi Wang ◽  
Yuehua Xu ◽  
Tengda Zhao ◽  
Zhilei Xu ◽  
Yong He ◽  
...  

Abstract The functional connectome is highly distinctive in adults and adolescents, underlying individual differences in cognition and behavior. However, it remains unknown whether the individual uniqueness of the functional connectome is present in neonates, who are far from mature. Here, we utilized the multiband resting-state functional magnetic resonance imaging data of 40 healthy neonates from the Developing Human Connectome Project and a split-half analysis approach to characterize the uniqueness of the functional connectome in the neonatal brain. Through functional connectome-based individual identification analysis, we found that all the neonates were correctly identified, with the most discriminative regions predominantly confined to the higher-order cortices (e.g., prefrontal and parietal regions). The connectivities with the highest contributions to individual uniqueness were primarily located between different functional systems, and the short- (0–30 mm) and middle-range (30–60 mm) connectivities were more distinctive than the long-range (>60 mm) connectivities. Interestingly, we found that functional data with a scanning length longer than 3.5 min were able to capture the individual uniqueness in the functional connectome. Our results highlight that individual uniqueness is present in the functional connectome of neonates and provide insights into the brain mechanisms underlying individual differences in cognition and behavior later in life.


2014 ◽  
Vol 91 (2) ◽  
pp. 20-39 ◽  
Author(s):  
Cyler Conrad ◽  
Allen Pastron

Spotting a sea turtle or Galapagos tortoise on the early wharfs and streets of San Francisco or Sacramento, California during the Gold Rush (1848-1855) would not have been a rare event. Massive population influx into the San Francisco Bay region during this time resulted in substantial impacts to native species and habitats of all taxa, but the demand for food resulted in many resources, turtles and tortoises included, being imported into the cities. Providing a fresh and delectable food source, these terrapin were brought to San Francisco and Sacramento to feed the hungry Gold Rush populous. Their taste, popularity and demand also resulted in small numbers being imported into gold mining towns in the San Joaquin Valley and foothills of the Sierra Nevada’s. Remarkable as this process was, the consumption and importation of both sea turtles and Galapagos tortoises during the Gold Rush pushed native populations of these species to the brink of extinction during the mid to late-nineteenth century. Declining numbers of terrapin and increased scientific curiosity, with a desire to safeguard these creatures for future generations, resulted in their eventually legal protection and conservation. In many ways the impacts of the decimation of terrapin in the eastern Pacific during the Gold Rush are still felt today, as conservation and breeding efforts continue in an attempt to return native turtle and tortoise populations to pre-Euro-American contact levels. This research describes the historical, and new archaeofaunal, evidence of the terrapin import market in San Francisco, Sacramento and beyond during the dynamic period of the California Gold Rush.


Phytotaxa ◽  
2015 ◽  
Vol 233 (3) ◽  
pp. 236 ◽  
Author(s):  
Roksana Majewska ◽  
J. P. Kociolek ◽  
Evan W. Thomas ◽  
Mario De Stefano ◽  
Mario Santoro ◽  
...  

Marine mammals such as whales and dolphins have been known for a long time to host a very specific epizoic community on their skin. Less known however is the presence of a similar community on the carapaces of sea turtles. The present study is the first describing new taxa inhabiting sea turtle carapaces. Samples, collected from nesting olive ridley sea turtles (Lepidochelys olivacea) on Ostional Beach (Costa Rica), were studied using light and scanning electron microscopy. Two unknown small-celled gomphonemoid taxa were analysed in more detail and are described as two new genera, closely related to other gomphonemoid genera with septate girdle bands, such as Tripterion, Cuneolus and Gomphoseptatum. Chelonicola Majewska, De Stefano & Van de Vijver gen. nov. has a flat valve face, uniseriate striae composed of more than three areolae, simple external raphe endings, internally a siliceous flap over the proximal raphe endings and lives on mucilaginous stalks. Poulinea Majewska, De Stefano & Van de Vijver gen. nov. has at least one concave valve, uniseriate striae composed of only two elongated areolae, external distal raphe endings covered by thickened siliceous flaps and lives attached to the substrate by a mucilaginous pad. Chelonicola costaricensis Majewska, De Stefano & Van de Vijver sp. nov. and Poulinea lepidochelicola Majewska, De Stefano & Van de Vijver sp. nov. can be separated based on stria structure, girdle structure composed of more than 10 copulae, raphe structure and general valve outline. A cladistics analysis of putative members of the Rhoicospheniaceae indicates that the family is polyphyletic. Chelonicola and Poulinea are sister taxa, and form a monophyletic group with Cuneolus and Tripterion, but are not closely related to Rhoicosphenia, or other genera previously assigned to this family. Features used to help diagnose the family such as symmetry and presence of septa and pseudosepta are homoplastic across the raphid diatom tree of life.


2018 ◽  
Author(s):  
Dale Squires ◽  
Victor Restrepo ◽  
Serge Garcia ◽  
Peter Dutton

This paper considers fisheries bycatch reduction within the least-cost biodiversity impact mitigation hierarchy. It introduces conservatory offsets that are implemented earlier in the biodiversity impact mitigation hierarchy than conventional compensatory offsets used as instruments of last resort. The paper illustrates implementation in an on-going sea turtle conservation programme by the International Seafood Sustainability Foundation.


Behaviour ◽  
2008 ◽  
Vol 145 (3) ◽  
pp. 297-312 ◽  
Author(s):  
Anne Savage ◽  
Joseph Soltis ◽  
Katherine Leighty ◽  
Kirsten Leong

AbstractFemale African elephants are thought to exchange 'rumble' vocalizations, but such temporally associated calls may not constitute communicative events. Affiliated females are more likely to engage in antiphonal calling, but affiliation is defined according to time spent in proximity. Affiliated partners may vocalize in sequence simply because their proximity causes them to collectively respond to shared external stimuli or due to a social facilitation effect. We used bi-variate and partial correlation analyses to test for the independent effects of the strength of the social relationship and distance between vocal partners on the likelihood of a vocal response. Female African elephants at Disney's Animal Kingdom were video-taped and outfitted with audio-recording collars that allowed for the individual identification of low-frequency rumbles. Affiliation had a strong influence on response likelihood, even after controlling for the effects of the distance between vocalizing partners. Further, the distance between vocalizing partners did not correlate with response likelihood, and factoring out the effects of affiliation did not significantly alter this result. These results suggest that rumble exchanges are communicative events that reflect social bonds, not simply artifacts of increased proximity and, therefore, provide support for functional hypotheses concerning rumble exchanges in wild African elephants.


1985 ◽  
Vol 63 ◽  
Author(s):  
M. P. Anderson ◽  
G. S. Grest ◽  
D. J. Srolovitz

The complete prediction of microstructural development in polycrystalline solids as a function of time and temperature is a major objective in materials science, but has not yet been possible primarily due to the complexity of the grain interactions. The evolution of the polycrystalline structure depends upon the precise specification of the coordinates of the grain boundary network, the crystallographic orientations of the grains, and the postulated microscopic mechanisms by which elements of the boundaries are assumed to move. Therefore, a general analytical solution to this multivariate problem has not yet been developed. Recently, we have been able to successfully incorporate these aspects of the grain interactions, and have developed a computer model which predicts the main features of the microstructure from first principles [1,2]., The polycrystal is mapped onto a discrete lattice by dividing the material into small area (2d) or volume (3d) elements, and placing the centers of these elements on lattice points. Interactions and dynamics are then defined for the individual elements which are analagous to those postulated in continuous systems. This discrete model preserves the topological features of real materials, and can be studied by computer simulation using Monte Carlo techniques. In this paper we report the application of the Monte Carlo method to the metallurgical phenomenon of grain growth with isothermal annealing. Extension of the model to treat primary recrystallization is presented elsewhere [3,4].


2011 ◽  
pp. 163-254
Author(s):  
Daijin Kim ◽  
Jaewon Sung

In the modern life, the need for personal security and access control is becoming an important issue. Biometrics is the technology which is expected to replace traditional authentication methods that are easily stolen, forgotten and duplicated. Fingerprints, face, iris, and voiceprints are commonly used biometric features. Among these features, face provides a more direct, friendly and convenient identification method and is more acceptable compared with the individual identification methods of other biometrics features. Thus, face recognition is one of the most important parts in biometrics.


Sign in / Sign up

Export Citation Format

Share Document