Automated Study of Greek Coins via Cluster Analysis

-
Automated  Study of Greek Coins via Cluster Analysis

OUTPUT




Background

One of the tools historians use when trying to understand the economies of ancient civilizations
is the die study. Researchers pore over collections of coins from a particular region and attempt to
determine which coins were created from the same engraving (die). From the number of dies in use in a region, these researchers can extrapolate about the economic health of the region at that time.
If each die depicted a completely different person or animal, the sorting process would be simple, but often coins will feature the same subject, even if they come from different dies. Since the dies were made by hand, no two dies were identical, but sometimes the differences can be as subtle as the shape of the nose or eye, details on the helmet, or the number of leaves in a palm branch. Since the studies are so time intensive, the corpus of studied coins is much smaller than the number of extant coins. Automating the process could generate much more information about commerce in ancient times. 

Problem Statement

Given scanned pages of coin pictures1, extract the individual coin images and then group them
based on distinctive features of the depicted subject.Algorithm
1. Image Acquisition – Binarize the scanned pages, and open with a circular structuring
element to eliminate any sparse text. Perform hole filling, if necessary, to complete the coin
masks. Then, for each detected coin, extract the pixels from that location and save those
pixels as an individual coin image.
2. Image Registration – For each coin, detect the foreground of the coin. Register coins so that
the foregrounds have the same size and orientation. Crop the edges of the coins so that
irregularities in coin edges are not captured in feature extraction.
3. Feature Extraction – Apply SIFT, Gabor (or other) wavelets, or some other feature extraction
tool to capture edge information on coin surface.
4. Clustering – Apply cluster analysis to the features. Initially, in order to determine feasibility,
I plan to do this with an algorithm like Lloyd’s algorithm (K-means) that requires K to be
known, but in order for the tool to be useful in the long run, this would need to use an
algorithm that estimates K, such as X-means.

Bibliography

Jain, Anil K. 2010. Data clustering: 50 years beyond K-means. Pattern Recogn. Lett. 31, 8 (June 2010),651-666. DOI=http://dx.doi.org/10.1016/j.patrec.2009.09.011

Liu, Chengjun and H. Wechsler. 2002. Gabor feature based classification using the enhanced fisher linear
discriminant model for face recognition. Trans. Img. Proc. 11, 4 (April 2002), 467-476.
DOI=http://dx.doi.org/10.1109/TIP.2002.999679
Pelleg, Dan and Andrew W. Moore. 2000. X-means: Extending K-means with Efficient Estimation of the
Number of Clusters. In Proceedings of the Seventeenth International Conference on Machine
Learning (ICML '00), Pat Langley (Ed.). Morgan Kaufmann Publishers Inc., San Francisco, CA,

FOR BASE PAPER MAIL US 

DOWNLOAD SOURCE CODE CLICK HERE

Comments

Post a Comment

Popular posts from this blog

Light Field Images for Background Removal

-
Image
Light Field Images for Background Removal OUTPUT OVERVIEW Standard edge detection or foreground/background separation techniques, such as Otzu’smethod, require color or intensity differences between the background and regions that need tobe separated. For example, green screens are routinely set up as the background in a scene so thatthere is a clear difference in color between the background and foreground.Light filed images, captured in 4D and passively containing depth information for thescene can be used to approximate this effect. Depth estimation in the scene alone could provide a metric to separate the foreground and background, but more sophisticated methods are available.Considering the edge detection from a single image from a single viewpoint and analyzing the depths from the light field around the edges in that image, occluded edges and intensity or color edges can be distinguished. Along with the rest of the depth information this can allow the foreground and b...
Read more

Using Image Processing to Identify and Score Darts thrown into a Dartboard

-
Image
✔️Using Image Processing to Identify and Score Darts thrown into a Dartboard ✔️Introduction The game of darts is a throwing sport in which participants toss projectiles into a circular target  attached to a vertical surface. The target is divided into many regions which correspond to different point and multiplier values. Darts is commonly played across North America and Europe and is a popular past time for many so an application that allows players to more conveniently keep score would be widely  beneficial. “Darts” is a general term for a targeting game following this basic premise and many game variations exist within this archetype; all utilizing the standard dart projectiles with a regulation dart board. Each game variant may have different objectives for which players to aim but identifying the region in  which the dart has hit in the dartboard is necessary for proper scoring. This project proposes the use of image processing to identify thrown da...
Read more

Face Detection, Extraction, and Swapping on Mobile Devices

-
Image
Face Detection, Extraction, and Swapping on Mobile Devices OUTPUT: DOCUMENTATION: We will use the Viola-Jones face detector in OpenCV as a starting point. Once we have found two faces we will apply some post processing to make sure that we have the entire face without any holes. Once we have a binary mask of the faces’ fully connected components, we plan to use cvBlobsLib (similar to regionprops function in Matlab) to do face region labelling and extraction. Choosing the faces to swap will either be random or done through a simple UI. Initially we will translate the faces to match the new face’s centroid with the centroid of the old face. Then, using the relative locations of features detected using OpenCV (such as the eyes, nose, and mouth) we will determine the orientation of the face in the plane parallel to the camera lens. Then, the relative sizes of these features will allow us to determine the degree of rotation away from the camera. However, if the faces we ar...
Read more