Search

Your search keyword '"Fernandez Jr., Proceso L."' showing total 6 results
Start Over "Fernandez Jr., Proceso L."
6 results on '"Fernandez Jr., Proceso L."'

1. Impact of Automatic Image Classification and Blind Deconvolution in Improving Text Detection Performance of the CRAFT Algorithm

Author

Albarillo, Clarisa V. and Fernandez Jr, Proceso L.

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Text detection in natural scenes has been a significant and active research subject in computer vision and document analysis because of its wide range of applications as evidenced by the emergence of the Robust Reading Competition. One of the algorithms which has good text detection performance in the said competition is the Character Region Awareness for Text Detection (CRAFT). Employing the ICDAR 2013 dataset, this study investigates the impact of automatic image classification and blind deconvolution as image pre-processing steps to further enhance the text detection performance of CRAFT. The proposed technique automatically classifies the scene images into two categories, blurry and non-blurry, by utilizing of a Laplacian operator with 100 as threshold. Prior to applying the CRAFT algorithm, images that are categorized as blurry are further pre-processed using blind deconvolution to reduce the blur. The results revealed that the proposed method significantly enhanced the detection performance of CRAFT, as demonstrated by its IoU h-mean of 94.47% compared to the original 91.42% h-mean of CRAFT and this even outperformed the top-ranked SenseTime, whose h-mean is 93.62%., Comment: 18 pages, 7 figures, 3rd International Conference on Machine Learning Techniques and Data Science

Published
2022
Full Text
View/download PDF

2. Parameterized Algorithm for the Poset Cover Problem.

Author

Ordanel, Ivy D., Fernandez Jr., Proceso L., Juayong, Richelle Ann B., Clemente, Jhoirene B., and Adorna, Henry N.

Subjects
*PARTIALLY ordered sets
Abstract

It is already known that the 1-Poset and 2-Poset Cover Problems are in 𝑷. In this paper, we extended the previous results and devised an algorithm for the 𝒌-Poset Cover Problem, for any 𝒌 number of posets that cover the input. The algorithm runs in 𝑶(𝒎2k 𝒏2), where 𝒎 and 𝒏 are the input size. With this running time, we can say that the problem belongs to XP (slicewise polynomial). The algorithm runs efficiently for small fixed 𝒌 but runs exponentially for large 𝒌. While the algorithm running time has yet not to be efficient for large 𝒌, we have shown a significant improvement from a brute-force solution, which runs in 2𝒎 𝒏2 + 𝑶(􀷌𝒌 𝒊 􀰸 1 2𝒎𝒊𝒏) - exponential even for small fixed [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

3. Improving the accuracy of the neighborhood median pixels method (NMPM) in classifying Landsat 8 OLI images by investigating the use of different neighborhood sizes.

Author

Moreno, Abigail S., Peñaflor, Christian V., Magpantay, Abraham T., and Fernandez Jr., Proceso L.

Subjects
LANDSAT satellites, NEIGHBORHOODS, REMOTE-sensing images, PIXELS, COMPUTER vision, REMOTE sensing, VEGETATION mapping
Abstract

Remote sensing has been used with various computer vision techniques in order to accurately classify different types of land covers from satellite images. One such technique is the Neighborhood Pixels Method, reported to have an overall accuracy of 94.0% in classifying vegetation, water, and built-up land cover from images taken from the Landsat 8 OLI satellite. In this study, we attempt to increase the accuracy of the technique by determining a more appropriate pixel neighborhood size. The previous study which developed the technique was first replicated, including the use of the same Landsat 8 OLI satellite images for training and testing, the building of lookup tables from the medians of 9x9 pixel neighborhoods, and the implementation of the same scoring system for the prediction step of the technique. Experiments on different neighborhood sizes were then conducted, with various statistics recorded for analysis and extracting insights. The overall accuracy of the original Neighborhood Pixels Method was shown to have improved by using other neighborhood sizes, with the highest average accuracy of 95.75% achieved by using 13x13 pixel neighborhoods. The results indicate that finding an appropriate neighborhood size can be an important step in accurately classifying varying land covers of a satellite image. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

5. Approximation and Computational Complexity of Some Hammock Variations of the Poset Cover Problem.

Author

Ordanel, Ivy D., Fernandez Jr., Proceso L., Juayong, Richelle Ann B., and Adorna, Henry N.

Subjects
*HAMMOCKS, *COMPUTATIONAL complexity, *APPROXIMATION theory, *PARTIALLY ordered sets, *LINEAR orderings
Abstract

The Hammock(2, 2 ,..., 2/k)-Poset Cover Problem is a variation of the Poset Cover Problem with the same input - set {L1, L2, ..., Lm} of linear orders over the set {1, 2, ..., n}, but the solution is restricted to a set of simple hammock(2, 2 ,..., 2/k) posets. The problem is NP-Hard when k = 3 but is in P when k = 1. The computational complexity of the problem when k = 2 is not yet known. In this paper, we determine the approximation complexity of the cases that have been shown to be NP-Hard. We show that the Hammock(2, 2 ,..., 2/k)-Poset Cover Problem is in APX and, in particular, (1 + 1/2K)-approximable, for k = 3. On the other hand, we also explore the computational complexity for the case where k = 2 [Hammock(2,2)-Poset Cover Problem]. We show that it is in P when the transposition graph of the input set of linear orders is rectangular. [ABSTRACT FROM AUTHOR]

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results