A Robust Image Enhancement Techniques for Underwater Fish Classification in Marine Environment

Pramunendar, Ricardus Anggi; Wibirama, Sunu; Santosa, Paulus Insap; Andono, Pulung Nurtantio; Soeleman, Moch Arief

doi:10.22266/ijies2019.1031.12

Cited by 10 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As demonstrated in Fig. (7), the combination method of GTCC and MFCC delivers a slight performance improvement over the MFCC method proposed by [9,13]. The proposed method incorporates attributes that disclose more information about each bird's voice characteristics than the GTCC features.…”

Section: Classificationmentioning

confidence: 91%

“…The resulting Cochleagram representation for each frame is calculated on average across the 𝑡 window and is defined in Eq. (7). Where 𝛾 is the dependent factor in frequency, and the other represents the magnitude of the complex number.…”

Section: • Windowingmentioning

confidence: 99%

“…The difference knowledge becomes an obstacle in recognizing all types of birds, especially if done manually in the open based on the abilities possessed by the limited human sense of hearing. Limitations cause differences in performance in grouping [7]. The role of the researcher is to find a way out of rules to make it easier for people to understand the animals around them [8].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Bird Voice Classification Based on Combination Feature Extraction and Reduction Dimension with the K-Nearest Neighbor

2022

IJIES

View full text Add to dashboard Cite

Indonesia is rich in flora and fauna diversity, but it is experiencing an increasing number of endangered populations. The public can prevent the expanding population threatened with extinction by knowing the types of fauna, especially birds threatened with extinction. This study proposes an automatic grouping method to recognize bird sound patterns in an open environment. This experiment used bird data from a public dataset and obtained bird sound patterns by recording from a distance far enough to make sounds without feeling disturbed freely. However, the sound of birds may contain noise and need data processing using YAMME to be carried out the noise, and birds' voices can be separated. After that, the data was extracted using the combination of Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) methods also reduced the dimensions of the feature before completing the identification. The bird identification obtained provides an accuracy performance that reaches 78.11%, and these results are higher than other feature extraction methods that also apply dimensional reduction.

show abstract

Section: Classificationmentioning

confidence: 91%

Section: • Windowingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Bird Voice Classification Based on Combination Feature Extraction and Reduction Dimension with the K-Nearest Neighbor

2022

IJIES

View full text Add to dashboard Cite

show abstract

“…When applying a high learning rate, the pattern created from the results of the accuracy performance based on the learning rate reveals that performance steadily falls. The solution is not ideal because the high learning rate and performance are reduced [34]. The momentum parameter is used to evaluate BPNN in Fig.…”

Section: Evaluation Of Bpnn Classification Based On Parametersmentioning

confidence: 99%

Effect of Feature Engineering Technique for Determining Vegetation Density

Sari¹,

Arifin²,

Novitasari³

et al. 2022

IJACSA

View full text Add to dashboard Cite

Vegetation density is one type of information collected from vegetation cover. Vegetation density influences evapotranspiration in terrain, which is essential in assessing how vulnerable peatlands are to fire. The Keetch and Byram Drought Index model, which evaluates peatland fire vulnerability, divides vegetation density into heavily grazed, softly grazed, and ungrazed. Manual approaches for analyzing vegetation density in the field, on the other hand, need a significant amount of resources. Image data acquisition, pre-processing, feature extraction, classification, feature selection, classification, and validation are all computer vision approaches used to solve these problems. Artificial intelligence algorithms and machine learning approaches promise outstanding accuracy in modern computer vision research. However, in the classification process, the impact of feature extraction is critical. Pattern identification at Back Propagation Neural Network (BPNN) is problematic because the feature extraction dimension is excessively complicated. The solution to this problem is using the feature engineering technique to choose the characteristics. This research aims to explore how feature engineering influences the accuracy of results. According to the statistics, implementing the recommended strategy can increase accuracy by 1% and increase kappa by 1.5%. This increase in vegetation density classification accuracy might help detect peatland vulnerability sooner. The novel aspect of this paper is that, after feature extraction, a feature engineering strategy is used in the machine learning classification stage to reduce the number of complex dimensions.

show abstract

“…This study proposed a combination of conventional image processing with deep learning to extract stone texts in natural scenes. Other studies on object recognition have also been carried out on fish recognition [9][10].…”

Section: Introductionmentioning

confidence: 99%

Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

Darma¹,

Suciati²,

Siahaan³

2020

IJIES

View full text Add to dashboard Cite

The preservation of Balinese carving data is a challenge in recognition of Balinese carving. Balinese carvings are a cultural heritage found in traditional buildings in Bali. The collection of Balinese carving images from public images can be a solution for preserving cultural heritage. However, the lousy quality of taking photographs, e.g., skewed shots, can affect the recognition results. Research on the Balinese carving recognition has existed but only recognizes a predetermined image. We proposed a Neural Style Geometric Transformation (NSGT) as a data augmentation technique for Balinese carvings recognition. NSGT is combining Neural Style Transfers and Geometric Transformations for a small dataset solution. This method provides variations in color, lighting, rotation, rescale, zoom, and the size of the training dataset, to improve recognition performance. We use MobileNet as a feature extractor because it has a small number of parameters, which makes it suitable to be applied on mobile devices. Eight scenarios were tested based on image styles and geometric transformations to get the best results. Based on the results, the proposed method can improve accuracy by up to 16.2%.

show abstract

A Robust Image Enhancement Techniques for Underwater Fish Classification in Marine Environment

Cited by 10 publications

References 19 publications

Bird Voice Classification Based on Combination Feature Extraction and Reduction Dimension with the K-Nearest Neighbor

Bird Voice Classification Based on Combination Feature Extraction and Reduction Dimension with the K-Nearest Neighbor

Effect of Feature Engineering Technique for Determining Vegetation Density

Neural Style Transfer and Geometric Transformations for Data Augmentation on Balinese Carving Recognition using MobileNet

Contact Info

Product

Resources

About