Automatic identification of landmarks in digital images

@article{Palaniswamy2010AutomaticIO,
  title={Automatic identification of landmarks in digital images},
  author={Sasirekha Palaniswamy and Neil A. Thacker and Christian Peter Klingenberg},
  journal={Iet Computer Vision},
  year={2010},
  volume={4},
  pages={247-260}
}
The authors present an automated system for feature recognition in digital images. Morphometric landmarks are points that can be defined in all specimens and located precisely. They are widely used in shape analysis and a typical shape analysis study involves several hundred digital images. Presently, the extraction of landmarks is usually done manually and the process of identifying the landmarks is an important and labour-intensive part of any such analysis. This process is time-consuming… 
Automatic identification system for morphometric landmarks
TLDR
The automatic extraction of morphometric landmarks in digital images of Drosophila is presented, showing the systematic variations between different individuals raises an issue relating to reliability and repeatability of this process of digitisation.
A Lightweight Keypoint Matching Framework for Morphometric Landmark Detection
TLDR
A novel approach for automatic landmark detection, based on visual features of landmarks and keypoint matching techniques, which requires less initial annotated data to build prediction model and runs faster than the state-of-the-art method.
MAELab: a framework to automatize landmark estimation
TLDR
This paper proposes a new approach to precisely estimate the landmark geometry, points of interest defined by biologists on the mandible contours, and defined patches around manual landmarks of the reference image to automatically register the landmarks on different mandibles.
Estimating landmarks on 2D images of beetle mandibles
TLDR
This work has implemented all the required algorithms to compute positions of mandibles landmarks and compared the obtained results to landmarks which have been manually set by biologists, finding that even positions automatically obtained are not fully precised.
An image database of Drosophila melanogaster wings for phenomic and biometric analysis
TLDR
An image database of Drosophila melanogaster wings is constructed - individually identifiable and organized by sex, genotype and replicate imaging system - for the development and testing of measurement and classification tools for biological images.
Outline-based morphometrics, an overlooked method in arthropod studies?
Landmarks Detection by Applying Deep Networks
TLDR
A convolutional neural network (CNN) is proposed to predict the landmarks on beetle images using a set of manually labeled landmarks dataset to provide the morphometric landmarks on biological images automatically.
ML‐morph: A fast, accurate and general approach for automated detection and landmarking of biological structures in images
TLDR
A machine‐learning‐based high‐throughput pipeline to collect high‐dimensional morphometric data in two‐dimensional images of semi‐rigid biological structures and a file conversion algorithm that can be used to leverage current morphometric datasets for automation, allowing the entire procedure, from model training all the way to prediction, to be performed in a matter of hours.
KALInA facial image analysis in anThropology : a revieW
TLDR
An overview of the methods used to analyse two-dimensional and three-dimensional, images, which are applicable to practical tasks of biological and forensic anthropology, and a study of face identification, which compares various approaches to dimension reduction and classification analysis and brings arguments in favour of robust image analysis that is based on robust statistical methodology.
...
...

References

SHOWING 1-10 OF 25 REFERENCES
Automatic Identification of Morphometric Landmarks in Digital Images
TLDR
The aim is to develop a completely automated and reliable system to identify morphological landmarks in digital images to replicate manual digitization with equivalent accuracy and reliability, based upon a small number of training examples.
Pairwise geometric histograms for object recognition : developments and analysis
TLDR
An algorithm is presented here that is able to recognise objects over a range of scale using the geometric histograms representation and a novel pairwise geometric histogram representation for arbitrary surfaces has been proposed.
Geometric feature distributions for shape representation and recognition
TLDR
The research reported in this thesis is directed toward the development of a scheme for representing the shape of an object which allows it to be recognised both quickly and robustly across a wide range of viewing conditions.
Robust Recognition of Scaled Shapes using Pairwise Geometric Histograms
TLDR
To improve the robustness of the recognition algorithm and to improve the accuracy to which an objects location, orientation and scale can be determined the generalised Hough transform has been replaced by the probabilistic Houghtransform.
A Computational Approach to Edge Detection
  • J. Canny
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 1986
TLDR
There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
The Use of Geometric Histograms for Model-Based Object Recognition
TLDR
It is shown that the geometric histograms used to record these distributions can be easily and robustly acquired from image data and can support recognition even when the shape extracted from the image is badly degraded by fragmentation noise and occlusion.
Landmark superimposition for taxonomic identification
TLDR
The results show that identification can be made simpler through the use of landmark configurations, and the basic hypothesis rests on the analogy between human fingerprints and organism landmark configuration.
Multiple shape recognition using pairwise geometric histogram based algorithms
TLDR
The present authors demonstrate the application of PGHs to recognition tasks involving very large model training sets and conclude that it is suitable for the recognition of very large numbers of objects.
An Analysis of Pairwise Geometric Histograms for View-Based Object Recognition
TLDR
The methods suggested in a previous paper for object recognition and location provide a complete solution to the problem of recognition of edge based descriptors for fixed 2D projected views of rigid objects.
...
...