Speeding-up Fractal Color Image Compression Using Moments Features Based on Symmetry Predictor

George, Loay E.; Al-Hilo, Eman A.

doi:10.1109/itng.2011.94

Cited by 5 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper proposed a solution by introducing an acceleration scheme to overcome KNN drawbacks via a combination of moment descriptors with traditional KNN. The moment descriptors have been utilized well in multimedia research for various applications, such as musical similarity and song year prediction [15], speed up color image fractal compression [16] and enhance fractal audio compression [17]. The training set will be arranged into subsets; samples belong to the same subset have similar descriptor number.…”

Section:  Issn: 1693-6930mentioning

confidence: 99%

Enhancement of student performance prediction using modified K-nearest neighbor

2020

View full text Add to dashboard Cite

The traditional K-nearest neighbor (KNN) algorithm uses an exhaustive search for a complete training set to predict a single test sample. This procedure can slow down the system to consume more time for huge datasets. The selection of classes for a new sample depends on a simple majority voting system that does not reflect the various significance of different samples (i.e. ignoring the similarities among samples). It also leads to a misclassification problem due to the occurrence of a double majority class. In reference to the above-mentioned issues, this work adopts a combination of moment descriptor and KNN to optimize the sample selection. This is done based on the fact that classifying the training samples before the searching actually takes place can speed up and improve the predictive performance of the nearest neighbor. The proposed method can be called as fast KNN (FKNN). The experimental results show that the proposed FKNN method decreases original KNN consuming time within a range of (75.4%) to (90.25%), and improve the classification accuracy percentage in the range from (20%) to (36.3%) utilizing three types of student datasets to predict whether the student can pass or fail the exam automatically.

show abstract

Section:  Issn: 1693-6930mentioning

confidence: 99%

Enhancement of student performance prediction using modified K-nearest neighbor

2020

View full text Add to dashboard Cite

show abstract

“…George method's used in combination with moment-based features (George and Al-Hilo, 2008; Al-Hilo and and DCT-based methods (George and Minas, 2011) as IFS transform invariants to be used as block descriptors; which in turn is utilized to classify the domain and range blocks. Furthermore, by adding the symmetry predictor that introduced in the method given in (George and Al-Hilo, 2011) that based on using first-order centralized moments; this predictor is useful to reduce the number of isometric trails from (8, that is, Rotation, reflection…etc.,) trials to (1) trail. Mahmoud, 2012 proposed the use of double moment descriptors to speed up FIC.…”

Section: Introductionmentioning

confidence: 99%

The Use of Quadtree Range Domain Partitioning with Fast Double Moment Descriptors to Enhance FIC of Colored Image

Sultan

George

Hassan

2018

ARO

View full text Add to dashboard Cite

In this paper, an enhanced fractal image compression system (FIC) is proposed; it is based on using both symmetry prediction and blocks indexing to speed up the blocks matching process. The proposed FIC uses quad tree as variable range block partitioning mechanism. two criteria's for guiding the partitioning decision are used: The first one uses sobel-based edge magnitude, whereas the second uses the contrast of block. A new set of moment descriptors are introduced, they differ from the previously used descriptors by their ability to emphasize the weights of different parts of each block. The effectiveness of all possible combinations of double moments descriptors has been investigated. Furthermore, a fast computation mechanism is introduced to compute the moments attended to improve the overall computation cost. the results of applied tests on the system for the cases "variable and fixed range" block partitioning mechanism indicated that the variable partitioning scheme can produce better results than fixed partitioning one (that is, 4 × 4 block) in term of compression ratio, faster than and PSNR does not significantly decreased.

show abstract