Research Article
Bread Wheat (Triticum aestivum L.) Variety Adaptation Trial for Moisture Stress Areas at Yabello District, Southern Oromia, Ethiopia
Belda Edeo*,
Ibsa Jibat,
Dajane Legassa
Issue:
Volume 11, Issue 2, June 2025
Pages:
18-26
Received:
14 January 2025
Accepted:
27 April 2025
Published:
12 June 2025
DOI:
10.11648/j.ijdst.20251102.11
Downloads:
Views:
Abstract: The field experiment was conducted at Yabello Onsite for three years; 2018, 2019 and 2023 on main cropping seasons. Six bread wheat varieties were evaluated. The trial was laid out in randomized complete block design (RCBD) with three replications. The experiment was objected to increase production and productivity of bread wheat and recommend best variety for agro-pastoralists and farmers in lowland agro-ecology and specifically to identify cultivars with better adaptability, high yielder and tolerant to drought. The combined analysis of variance showed that there was significant difference among varieties in yield and yield related traits in all cropping years. The highest grain yield was obtained from “Amibara-2” variety (3918.2 kg/ha) followed by “Fentalle-2” (3700.5 kg/ha) while the lowest grain yield was recorded from werer-2 variety (3073.8 kg/ha). The result of the experiment suggests conducting research work on adaption trials of different crop enhances production and productivity for end users. Therefore, the identified varieties were suggested for further demonstration and popularization in Borana lowland and areas with similar agro-ecology.
Abstract: The field experiment was conducted at Yabello Onsite for three years; 2018, 2019 and 2023 on main cropping seasons. Six bread wheat varieties were evaluated. The trial was laid out in randomized complete block design (RCBD) with three replications. The experiment was objected to increase production and productivity of bread wheat and recommend best...
Show More
Research Article
RanPil: New Dataset and Benchmark for Offline Handwritten Korean Text Recognition
Hyon-Gwang O,
Myong-Chol Kim,
Il-Nam Pak,
Un-Hyok Choe,
Chol-Jun O*
Issue:
Volume 11, Issue 2, June 2025
Pages:
27-34
Received:
7 April 2025
Accepted:
27 April 2025
Published:
20 June 2025
DOI:
10.11648/j.ijdst.20251102.12
Downloads:
Views:
Abstract: In recent years, since deep learning technology have been applied to handwritten text recognition, the need for handwritten document image Datasets has been growing more and more. In particular, the development of the dataset is of great significance for improving performance of handwritten Korean text recognition because no dataset for handwritten Korean text recognition has been published. In this paper, we present the “RanPil”, a new training and performance evaluation dataset for handwritten Korean text recognition, which consists of a total of 8,600 pages of images (182,000 text lines and 4,300,000 characters) written by 1,804 people. We evaluate writing- diversity of handwritten document images, such as text line spacing, text line slope, character size, word spacing, and character compactness. In addition, we propose an MOS (Mean Opinion Score) evaluation method for the scrawl-level. Finally, we evaluate the performance of TrOCR based on vision encoder and decoder with a test dataset classified by the scrawl-levels.
Abstract: In recent years, since deep learning technology have been applied to handwritten text recognition, the need for handwritten document image Datasets has been growing more and more. In particular, the development of the dataset is of great significance for improving performance of handwritten Korean text recognition because no dataset for handwritten...
Show More
