Loading...
Loading...
Contributors:
Dataset URI:
doi:10.7910/DVN/CP4IVFThis image dataset compiled for the purpose of machine learning-based identification and prediction of adulteration levels in Chili Pepper (Capsicum annuum) powder. The dataset includes images of pure Mareko, and Elos Chili Pepper powder varieties, two types of bricks powders, as well as Mareko, and Elos Chili Pepper powder varieties adulterated with two types of bricks powders.The images dataset were prepared — First, the pods of Mareko and Elos Chili Pepper varieties freshly harvested, dried naturally, and milled as a common practice among its consumers. A total weight of 100 grams of pure Chili pepper powder, with each Chili pepper variety weighing between 60 grams and 90 grams, was mixed with brick powder type 1, which ranged from 10 grams (10%) to 40 grams (40%), using increasing weight ratios of 5 grams (5%) in seven categories of adulteration. However, brick powder type 2 was mixed with both Mareko Chili pepper powder and Elos Chili pepper powder in five levels of adulteration ranging from 10 grams (10%) to 30 grams (30%). Using 300 W incandescent lamps light source, a total weight of 100 grams of each pure and adulterated Chili pepper powder was placed inside a 10 cm x 10 cm plastic box that placed 30 cm away from camera lens. And 3,000 number of raw pictures captured using a top-view 18 megapixels Canon (Model EOS 7D) camera. Also, to enhance the dataset's diversity and quantity, by processing the raw images, 20,600 augmented images in total were created. The augmented images that are generated are 2,800 augmented images by cropping the raw image, except for the pure adulterant images, into 2048 rows by 2028 columns to isolate the chili pepper powder part; 2,800 augmented images using the super-resolution (SwinIR-L with GAN) 4x model to scale up 4 times the resolution of the raw image, except for the pure adulterant images; and 17,800 using pixel location shuffling in five block sizes of 1x1, 2x2, 4x4, 8x8, and 16x16. This dataset is a valuable resource for researchers and students in Chili Pepper powder adulteration using image processing and feature extraction. It also holds potential for use by Food and Drug Administration Authorities and law enforcement to develop automated methods for detecting Chili Pepper powder adulteration, offering an alternative to time-consuming physio-chemical laboratory tests. The dataset's structure and augmentation methods are detailed to ensure reproducibility and encourage further research into robust machine learning models for food quality control.
Keyword(s):
MeSH Term(s):
Grants and Funding:
No Grants or Funding Data Available
Associated Publication(s):
No Associated Publication Data Available
Supplementary Data:
No Supplementary Data Available
Related Dataset(s):
No Related Dataset Data Available
The National Library of Medicine (NLM) provides information about biomedical datasets. Inclusion on an NLM Web page does not imply endorsement of, or agreement with, the contents by NLM or the National Institutes of Health. Learn more: NLM Web Policies (nih.gov)