AIRLINK 154.88 Increased By ▲ 4.63 (3.08%)
BOP 9.96 Decreased By ▼ -0.16 (-1.58%)
CNERGY 7.33 Decreased By ▼ -0.09 (-1.21%)
CPHL 78.24 Increased By ▲ 7.11 (10%)
FCCL 47.53 Increased By ▲ 1.82 (3.98%)
FFL 14.49 Increased By ▲ 0.15 (1.05%)
FLYNG 40.87 Increased By ▲ 3.72 (10.01%)
HUBC 138.71 Increased By ▲ 0.36 (0.26%)
HUMNL 12.93 Increased By ▲ 0.39 (3.11%)
KEL 4.34 Decreased By ▼ -0.22 (-4.82%)
KOSM 5.16 Increased By ▲ 0.17 (3.41%)
MLCF 75.92 Increased By ▲ 6.27 (9%)
OGDC 218.66 Increased By ▲ 15.65 (7.71%)
PACE 5.23 Decreased By ▼ -0.15 (-2.79%)
PAEL 45.30 Increased By ▲ 1.06 (2.4%)
PIAHCLA 14.80 Increased By ▲ 1.35 (10.04%)
PIBTL 8.64 Increased By ▲ 0.02 (0.23%)
POWER 15.13 Increased By ▲ 0.15 (1%)
PPL 168.03 Increased By ▲ 15.28 (10%)
PRL 29.55 Increased By ▲ 2.53 (9.36%)
PTC 20.13 Increased By ▲ 0.84 (4.35%)
SEARL 82.57 Increased By ▲ 7.51 (10.01%)
SSGC 32.79 Increased By ▲ 2.33 (7.65%)
SYM 14.23 Increased By ▲ 0.28 (2.01%)
TELE 6.99 Increased By ▲ 0.08 (1.16%)
TPLP 8.26 Increased By ▲ 0.26 (3.25%)
TRG 63.29 Increased By ▲ 1.39 (2.25%)
WAVESAPP 9.05 Increased By ▲ 0.11 (1.23%)
WTL 1.26 Decreased By ▼ -0.06 (-4.55%)
YOUW 3.61 Decreased By ▼ -0.12 (-3.22%)
AIRLINK 154.88 Increased By ▲ 4.63 (3.08%)
BOP 9.96 Decreased By ▼ -0.16 (-1.58%)
CNERGY 7.33 Decreased By ▼ -0.09 (-1.21%)
CPHL 78.24 Increased By ▲ 7.11 (10%)
FCCL 47.53 Increased By ▲ 1.82 (3.98%)
FFL 14.49 Increased By ▲ 0.15 (1.05%)
FLYNG 40.87 Increased By ▲ 3.72 (10.01%)
HUBC 138.71 Increased By ▲ 0.36 (0.26%)
HUMNL 12.93 Increased By ▲ 0.39 (3.11%)
KEL 4.34 Decreased By ▼ -0.22 (-4.82%)
KOSM 5.16 Increased By ▲ 0.17 (3.41%)
MLCF 75.92 Increased By ▲ 6.27 (9%)
OGDC 218.66 Increased By ▲ 15.65 (7.71%)
PACE 5.23 Decreased By ▼ -0.15 (-2.79%)
PAEL 45.30 Increased By ▲ 1.06 (2.4%)
PIAHCLA 14.80 Increased By ▲ 1.35 (10.04%)
PIBTL 8.64 Increased By ▲ 0.02 (0.23%)
POWER 15.13 Increased By ▲ 0.15 (1%)
PPL 168.03 Increased By ▲ 15.28 (10%)
PRL 29.55 Increased By ▲ 2.53 (9.36%)
PTC 20.13 Increased By ▲ 0.84 (4.35%)
SEARL 82.57 Increased By ▲ 7.51 (10.01%)
SSGC 32.79 Increased By ▲ 2.33 (7.65%)
SYM 14.23 Increased By ▲ 0.28 (2.01%)
TELE 6.99 Increased By ▲ 0.08 (1.16%)
TPLP 8.26 Increased By ▲ 0.26 (3.25%)
TRG 63.29 Increased By ▲ 1.39 (2.25%)
WAVESAPP 9.05 Increased By ▲ 0.11 (1.23%)
WTL 1.26 Decreased By ▼ -0.06 (-4.55%)
YOUW 3.61 Decreased By ▼ -0.12 (-3.22%)
BR100 12,644 Increased By 241 (1.94%)
BR30 37,293 Increased By 1733.2 (4.87%)
KSE100 118,576 Increased By 1278.2 (1.09%)
KSE30 36,302 Increased By 462.9 (1.29%)
Technology

AI-based Rice Quality Analyser to transform Pakistan's Rice sector

  • NED Student has developed Pakistan’s first AI-based Rice Quality Analyser to test the quality of rice grain in less than 60 seconds.
Published October 10, 2020

The first ever Pakistan AI-based ‘Rice Quality Analyser’ is successfully developed by students at the National Center of Artificial Intelligence (NCAI) at the NED University, in collaboration with Rice Lab Pakistan.

This software uses Machine Learning to analyse the quality of rice grain in less than 60 seconds. The analysis is based on 7 main characteristics of rice grain: length, thickness, average weight, and percentage of broken grains.

This Rice Quality Analyser developed in Pakistan has an accuracy rate of 99%, which is similar to modern Japanese and American rice quality analysers. However, the Pakistani version is much more effective than the Japanese ones and much cheaper than the one developed in the United States.

With Pakistan being the world’s 10th largest rice producer in the world, the quality of rice grain significantly impacts its price and export-potential. Previously, the quality of rice has been determined through a traditional process, which takes in a sample of 8 kg rice and assesses its quality using the human eye. This process costs a lot in terms of time and money, and is mostly deemed as ineffective.

Instead, this Pakistan-bred Rice Quality Analyser improves the local rice testing capacity through the use of AI technology. It is also faster and less expensive. Moreover, this new technology takes into account Pakistan’s atmospheric conditions and complies with national rice industry standards.

According to Hafiz Ahsan-ur-Rehman, a research associate at the NCAI and a member of the Rice Quality Analyzer Software Development Team, this new AI software is a key achievement for Pakistan’s rice sector.

This state-of-the-art software will reduce the time taken to complete rice export orders by decreasing the cost of rice classification and increasing testing capacity.

This Rice Quality Analyser will collect scanned images of rice grains. Traders and millers can use any good quality flat bed scanner to do that. The images are then sent to the Smart City Lab team, which immediately analyses the rice grains and then sends back results via email. Currently, the Smart City Lab Country is offering a free trial to popularize this innovative software.

Hafiz adds that although the marketing campaign for this new technology is still in process, they have received positive reactions from major rice-producing countries like China, Indonesia, India and Bangladesh.

Comments

Comments are closed.