基于百度AI卷積神經(jīng)網(wǎng)絡(luò)的茶樹結(jié)霜智能識(shí)別

doi:10.12306/2021jms.0080

首頁(yè) > 過刊瀏覽>2023年第43卷第2期 >245-253. DOI:10.12306/2021jms.0080

基于百度AI卷積神經(jīng)網(wǎng)絡(luò)的茶樹結(jié)霜智能識(shí)別
DOI:
                        10.12306/2021jms.0080
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡(jiǎn)介:
通訊作者:
中圖分類號(hào):P49
基金項(xiàng)目:浙江省重點(diǎn)研發(fā)計(jì)劃項(xiàng)目（2021C02036）；浙江省氣象科技重點(diǎn)項(xiàng)目（2019ZD16；2019ZD17）；國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目（2019YFD1002203）

Intelligent recognition of tea frost based on Baidu AI convolutional neural network

Author:

Affiliation:

Fund Project:

摘要

圖/表

訪問統(tǒng)計(jì)

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

資源附件

文章評(píng)論

摘要:

基于采集的近20 000張茶園圖像，分別篩選出1 000張茶園結(jié)霜和1 000張未結(jié)霜圖像作為訓(xùn)練樣本，利用百度AI開放平臺(tái)的EasyDL經(jīng)典版圖像識(shí)別功能，應(yīng)用卷積神經(jīng)網(wǎng)絡(luò)算法，建立茶園結(jié)霜識(shí)別模型，進(jìn)行茶樹結(jié)霜圖像智能判別。茶樹結(jié)霜智能識(shí)別模型的準(zhǔn)確率、F1評(píng)分、精確率、召回率分別為99.2%、99.2%、99.3%、99.1%。模型檢驗(yàn)結(jié)果為：樣本地20張結(jié)霜圖像的平均識(shí)別置信度為95.51%，20張非結(jié)霜圖像的平均識(shí)別置信度為99.99%；非樣本地（江南茶區(qū)）80張結(jié)霜圖像的平均識(shí)別置信度為97.53%，80張非結(jié)霜圖像的平均識(shí)別置信度為95.11%。

Abstract:

There are 1 000 frosted and 1 000 non-frosted images of tea gardens were selected as training samples from nearly 20 000 images of tea gardens, and the tea garden frost model was established by using the EasyDL image recognition function of Baidu AI open platform in order to intelligently recognize the tea garden frosting. The accuracy rate, F1-score, precision rate and recall rate of the tea garden frost model were 99.2%, 99.2%, 99.3% and 99.1%, respectively. The model test results showed that the average recognition confidence of 20 frosted images was 95.51%, and the average recognition confidence of 20 non-frosted images was 99.99%. The average recognition confidence of 80 frosted images in the non-sample area (tea area in Jiangnan) was 97.53%, and the average recognition confidence of 80 non-frosted images was 95.11%.

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

引用本文

朱蘭娟,胡德云,華行祥,李時(shí)睿,楊欣潔,張旭暉.基于百度AI卷積神經(jīng)網(wǎng)絡(luò)的茶樹結(jié)霜智能識(shí)別.氣象科學(xué),2023,43(2):245-253 ZHU Lanjuan, HU Deyun, HUA Xingxiang, LI Shirui, YANG Xinjie, ZHANG Xuhui. Intelligent recognition of tea frost based on Baidu AI convolutional neural network. Journal of the Meteorological Sciences,2023,43(2):245-253

復(fù)制

文章指標(biāo)

點(diǎn)擊次數(shù):
下載次數(shù):
HTML閱讀次數(shù):
引用次數(shù):

歷史

收稿日期:2021-03-09
最后修改日期:2021-09-22
錄用日期:
在線發(fā)布日期: 2023-05-20
出版日期: 2023-04-15

文章二維碼

您是第位訪問者
氣象科學(xué) ® 2026 版權(quán)所有
技術(shù)支持：北京勤云科技發(fā)展有限公司

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標(biāo)

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒 激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標(biāo)

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说