SIMPLE Descriptors (Extended)

SIMPLE (Searching Images with Mpeg-7 & Mpeg-7 like Powered Localized dEscriptors) family of features began as a collection of four descriptors (Simple-SCD, Simple-CLD, Simple-EHD, and Local-CEDD or LoCATe). The main idea behind SIMPLE is to utilize global descriptors as local ones. To do this, the SURF detector was initially employed to define regions of interest on an image, and instead of using the SURF descriptor, one of the MPEG-7 SCD, the MPEG-7 CLD, the MPEG-7 EHD, and the CEDD descriptors are utilized to extract the features of those image’s patches. Finally, the Bag-Of-Visual-Words framework is used to test the performance of those descriptors in CBIR tasks.

Furthermore, recently SIMPLE was extended from a collection of descriptors (the latest addition is Local CoMo), to a scheme (a combination of a detector and a global descriptor). Tests have been carried out after utilizing other detectors — the SIFT detector and two Random Image Patches’ Generators. The Random Generator has produced the best results and is portrayed as the preferred choice.

From this page, one can download the official open source implementation of the SIMPLE descriptors (C#, Java, and MATLAB)

Searching Images with MPEG-7 (& MPEG-7 Like) Powered Localized dEscriptors (SIMPLE) A set of local image descriptors specifically designed for image retrieval tasks

Image retrieval problems were first confronted with algorithms that tried to extract the visual properties of a depiction globally, following the human instinct of evaluating an image’s content. Experimenting with retrieval systems and evaluating their results, especially on verbose images and images where objects appear with partial occlusions, showed that the accepted correctly ranked results are positively evaluated by the extraction of the salient regions of an image rather than the overall depiction. Thus, representing the image by its points of interest proved to be a more robust solution. SIMPLE descriptors emphasize and incorporate the characteristics that allow a more abstract but retrieval-friendly description of the image’s salient patches. Experiments were contacted on several well-known benchmarking databases. A detailed presentation of the results is available [Here] and [Here]

Downloads

  • SIMPLE Descriptors with Random Image Patches’ Generator (Suggested Implementation) – Java Source Code [Download] (GNU GPL).
  • SIMPLE Descriptors with Random Image Patches’ Generator – C# Source Code and DLL [Download] (GNU GPL).

For C# implementation:

This is the easiest way to incorporate in your application the SIMPLE descriptors (no external dependencies). Simply add the dll as a reference in your c# project and then call the classes as

Capture

* The Number 600 refers to the number of samples per image. For the other SIMPLE Descriptors, simply select another method from the SIMPLE class

SIMPLE Descriptors

  • Download an example application in which we describe the retrieval procedure using the above DLL. Source Code included – C# Source Code [Download] (GNU GPL)

  • SIMPLE Descriptors with SIFT and SURF Detector as Patches’ Generator (64) – C# Source Code and DLL [Download] (GNU GPL)
  • SIMPLE Descriptors with SIFT and SURF Detector as Patches’ Generator (32)- C# Source Code and DLL [Download] (GNU GPL)
  • SIMPLE Descriptors with Gaussian Random Image Patches’ Generator – C# Source Code and DLL [Download] (GNU GPL)
  • Download an example application in which we describe the retrieval procedure. Source Code included – C# Source Code [Download] (GNU GPL)
  • Third-party tutorial (Special thanks to SHABBIR AKOLAWALA)

SIMPLE-Locate Descriptor with SURF – MATLAB Source Code [Download] (FAPO*) 

The source code is simple and easy to handle by all users. There is a main function that has the task of extracting the LoCATe descriptor from a given image [*] For academic purposes only

A LoCATe-based Visual Place Recognition System for Mobile Robotics and GPGPUs

This approach describes a novel visual Place Recognition (vPR) approach based on a visual vocabulary of the Local CEDD descriptor to address the loop closure detection task. Experiments show that the usage of CEDD as a local descriptor produces high accuracy vPR results, while the parallelization employed allows for a real-time implementation even in the case of a low-cost mobile device.


Additional Staff:

Slides from the first presentation of the SIMPLE descriptors @ CBMI2014: