News classification
Contact us
- Add: No. 9, North Fourth Ring Road, Haidian District, Beijing. It mainly includes face recognition, living detection, ID card recognition, bank card recognition, business card recognition, license plate recognition, OCR recognition, and intelligent recognition technology.
- Tel: 13146317170 廖经理
- Fax:
- Email: 398017534@qq.com
Image recognition technology, plant identification accuracy rate as high as 80%, botanist much easier
Image recognition technology, plant identification accuracy rate as high as 80%, botanist much easier
Natural history museums around the world are speeding up the process of digital collections, storing specimen images in open databases. For example, a database of the National Science Foundation's iDigBio project has more than 150 million images of plants and animals from all over the United states.
Only a small fraction of the world's 350 million species have been digitized. However, with the progress of computing technology, Costa Rica Institute of computer scientist Eric Montanaro of France and Montpelier International Agricultural Development Research Center of the botanist Pierre Bonnet believes that it is possible to sample bigger data set. Their team has achieved the automation of plant identification. AI
Researchers use intelligent mobile phone application scene were fresh plant accumulated millions of images, and then scanned the identification of more than 1000 species, more than 260 thousand herbarium specimens, using the advanced algorithm recognition accuracy rate is as high as 80%.
Such astonishing results, Bonnet says, often leave botanists worried that their academic field is being looked down upon. "But human expertise will never be eliminated, and the results need to be tested by botanists."."
Artificial intelligence method to identify specimens, greatly reduce the recognition time were collected and botanist, can help improve the level of plant identification data were poor, the rich in biodiversity but less areas particularly useful plant specimens.
In addition, this approach allows researchers to perform additional analysis of large data. In general, plant specimens contain abundant data, such as time and place of collection, flowering or results in the collection, and floral characteristics. Since some samples were data several centuries ago, they can help to study how plants adapt to climate change.
Dr Peter Wilf, of the Penn State University, said: "in the course of natural history, this approach bodes for the future."."
Science and technology daily chief editor punctuate
Botanists seem to be able to free themselves from heavy collection and identification of specimens. If the results are stable, they can save at least 80% of the time! You know, there are more and more digital specimens in the natural history museum around the world, and there are more than 150 million images in a single database. Artificial intelligence can automatically identify specimens, which is certainly not a threat to botanists. After all, most of the work is boring and boring, but crucial, and artificial intelligence helps in these areas, and it really doesn't make you any more intimate. Opening a brain cavity, and if scientists can give artificial intelligence to the tedious and what they have to do, will the output of science be more abundant?
Only a small fraction of the world's 350 million species have been digitized. However, with the progress of computing technology, Costa Rica Institute of computer scientist Eric Montanaro of France and Montpelier International Agricultural Development Research Center of the botanist Pierre Bonnet believes that it is possible to sample bigger data set. Their team has achieved the automation of plant identification. AI
Researchers use intelligent mobile phone application scene were fresh plant accumulated millions of images, and then scanned the identification of more than 1000 species, more than 260 thousand herbarium specimens, using the advanced algorithm recognition accuracy rate is as high as 80%.
Such astonishing results, Bonnet says, often leave botanists worried that their academic field is being looked down upon. "But human expertise will never be eliminated, and the results need to be tested by botanists."."
Artificial intelligence method to identify specimens, greatly reduce the recognition time were collected and botanist, can help improve the level of plant identification data were poor, the rich in biodiversity but less areas particularly useful plant specimens.
In addition, this approach allows researchers to perform additional analysis of large data. In general, plant specimens contain abundant data, such as time and place of collection, flowering or results in the collection, and floral characteristics. Since some samples were data several centuries ago, they can help to study how plants adapt to climate change.
Dr Peter Wilf, of the Penn State University, said: "in the course of natural history, this approach bodes for the future."."
Science and technology daily chief editor punctuate
Botanists seem to be able to free themselves from heavy collection and identification of specimens. If the results are stable, they can save at least 80% of the time! You know, there are more and more digital specimens in the natural history museum around the world, and there are more than 150 million images in a single database. Artificial intelligence can automatically identify specimens, which is certainly not a threat to botanists. After all, most of the work is boring and boring, but crucial, and artificial intelligence helps in these areas, and it really doesn't make you any more intimate. Opening a brain cavity, and if scientists can give artificial intelligence to the tedious and what they have to do, will the output of science be more abundant?