ﻪﺑ نﺎﮑﻣا ﯽﺳرﺮﺑ شور يﺮﯿﮔرﺎﮐ
ﺺﯿﺨﺸﺗ ﺖﻬﺟ لﺎﺘﯿﺠﯾد ﺮﯾوﺎﺼﺗ شزادﺮﭘ
يرﺎﻤﯿﺑ ﺞﻧﺮﺑ گﺮﺑ ﺢﻄﺳ يﺎﻫ
ﺳ ﯿ ﺪ ﺴﺣ ﯿ ﻦ ﭘ ﯿ
1نﺎﻤ - *
ﺸﺨﺑ لدﺎﻋ ﯽ
ز رﻮﭘ ﯾ ﻫﺎﮕﺗرﺎ
2ﯽ - ﺮﻔﻌﺟ سﺎﺒﻌﻟاﺪﺒﻋ
3ي
ﺖﻓﺎﯾرد ﺦﯾرﺎﺗ :
18 / 11 / 1392
شﺮﯾﺬﭘ ﺦﯾرﺎﺗ :
26 / 06 / 1393
هﺪﯿﮑﭼ
،يزروﺎﺸﮐ ﻦﯾﻮﻧ ﺚﺣﺎﺒﻣ رد شور ﯽﺳرﺮﺑ
يرﺎـﻤﯿﺑ ﺺﯿﺨـﺸﺗ ياﺮﺑ ﻖﯿﻗد و نازرا ،رﺎﮐدﻮﺧ ،ﻊﯾﺮﺳ يﺎﻫ ﺖـﺳا رادرﻮـﺧﺮﺑ يدﺎـﯾز ﺖـﯿﻤﻫا زا هﺎـﯿﮔ يﺎـﻫ
.
يرﺎﻤﯿﺑ ﺎﺑ ﻪﻠﺑﺎﻘﻣ يﺎﻫرﻮﺘﮐﺎﻓ ﻦﯾﺮﺘﻤﻬﻣ زا ،عراﺰﻣ رد يرﺎﻤﯿﺑ ﻖﯿﻗد و ﻊﻗﻮﻣ ﻪﺑ ﺺﯿﺨﺸﺗ ﯽﻣ ﯽﻫﺎﯿﮔ يﺎﻫ
ﺪﺷﺎﺑ . ﺮﯾﻮـﺼﺗ شزادﺮﭘ ﮏﯿﻨﮑﺗ ﯽﯾﺎﻧاﻮﺗ ﻖﯿﻘﺤﺗ ﻦﯾا رد
ﺞﻧﺮﺑ ﻢﻬﻣ يرﺎﻤﯿﺑ ود ﺺﯿﺨﺸﺗ رد )
هﻮﻬﻗ ﻪﮑﻟ ﺞﻧﺮﺑ گﺮﺑ ﺖﺳﻼﺑ و يا (
ﺖﻓﺮﮔ راﺮﻗ ﯽﺳرﺮﺑ درﻮﻣ . ﺗ
گﺮﺑ زا لﺎﺘﯿﺠﯾد ﺮﯾوﺎﺼ يﺎﻫ
ﺪﻧﺪـﺷ ﻪـﯿﻬﺗ هدﻮﻟآ ﺞﻧﺮﺑ هﺎﯿﮔ .
ﺪﻧﺪﺷ شزادﺮﭘ ﺐﻠﺘﻣ راﺰﻓا مﺮﻧ ﺮﯾﻮﺼﺗ شزادﺮﭘ راﺰﺑا ﻪﺒﻌﺟ رد ﺮﯾوﺎﺼﺗ .
ﻪﺑ ﯽﮕﻧر شزادﺮﭘ زا ﻪﮑﻟ يزﺎﺳاﺪﺟ رﻮﻈﻨﻣ
ﺖﻤﺴﻗ يﺮﻫﺎﻇ يﺎﻫ گﺮﺑ ﺢﻄﺳ زا هدﻮﻟآ يﺎﻫ
ﺪﺷ هدﺎﻔﺘﺳا . ﺖﺴﻧاﻮﺗ هﺪﺷ ﻪﺋارا ﻢﺘﯾرﻮﮕﻟا ﻪﮐ داد نﺎﺸﻧ ﺞﯾﺎﺘﻧ هدﻮﻟآ طﺎﻘﻧ
ار ﻪﻧﻮﻤﻧ رد ﺮﯾوﺎﺼﺗ درﻮﻣ ﺖﻗد ﺎﺑ ﺶﯾﺎﻣزآ 4/
97
% ﺪﻫد ﺺﯿﺨﺸﺗ .
عﻮـﻧ ود ﻦﯿـﺑ ﺰﯾﺎﻤﺗ
ﺖﻫﺎﺒﺷ ﻞﯿﻟد ﻪﺑ يرﺎﻤﯿﺑ يرﺎﻤﯿﺑ ﻢﺋﻼﻋ ﯽﮕﻧر يﺎﻫ
ًﺎﺒﯾﺮﻘﺗ ﺎﻫ دﻮﺑ ﻦﮑﻤﻣ ﺮﯿﻏ .
ﺪﯿﻔـﺳ و هﺎﯿـﺳ ﺮﯾوﺎﺼﺗ زا ﯽﻠﮑﺷ تﺎﯿﺻﻮﺼﺧ ،ﺺﯿﺨﺸﺗ دﻮﺒﻬﺑ رﻮﻈﻨﻣ ﻪﺑ ﻦﯾاﺮﺑﺎﻨﺑ
گﺮﺑ ﺪﻧﺪﺷ جاﺮﺨﺘﺳا هدﻮﻟآ ﺎﻫ .
ﯽﮔﮋﯾو ﺪﻨﻧﺎﻣ ﺪﻌﺑ نوﺪﺑ يﺎﻫ ﺖﻤﺴﻗ ﺢﻄﺳ ﺖﺒﺴﻧ و ﯽﮔدﺮﺸﻓ ،يﺮﻫﺎﻇ ﺖﺒﺴﻧ ،يدﺮﮔ
هﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ ﻪﺑ طﻮﺑﺮﻣ هدﻮﻟآ يﺎﻫ يا
ﺪﻨﺘﻓﺮﮔ راﺮﻗ ﯽﺳرﺮﺑ درﻮﻣ و هﺪﺷ جاﺮﺨﺘﺳا ﺞﻧﺮﺑ گﺮﺑ ﺖﺳﻼﺑ و .
ﺎﺑ لدﺎﻌﻣ ﯽﺘﻗد 6/
96
% ﻪﺑ ﻢﺘﯾرﻮﮕﻟا ياﺮﺑ نﺎﺸﻧ ﻪﮐ ﺪﻣآ ﺖﺳد
ود ﺺﯿﺨـﺸﺗ رد ﯽﯾﺎﻧاﻮﺗ هﺪﻨﻫد
هﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ دﻮﺑ ﺞﻧﺮﺑ گﺮﺑ ﺖﺳﻼﺑ و يا
.
و هژا يﺎﻫ يﺪﯿﻠﮐ :
،ﺞﻧﺮﺑ ﺖﺳﻼﺑ ،ﺞﻧﺮﺑ هﻮﻬﻗ ﻪﮑﻟ
ﯽﯾﺎﻨﯿﺑ ﻦﯿﺷﺎﻣ ،يا
ﻪﻣﺪﻘﻣ
1
ﺞﻧﺮـﺑ )
Oryza Sativa L.
( ﯽﻤﯾﺪـﻗ زا ﯽــﮑﯾ ﻦﯾﺮــﺘﻤﻬﻣ و ﻦﯾﺮـﺗ
ﯽـﻣ ﺖﺸﮐ نﺎﻬﺟ طﺎﻘﻧ زا يرﺎﯿﺴﺑ رد ﻪﮐ ﺖﺳا ﯽﯾاﺬﻏ تﻻﻮﺼﺤﻣ دﻮـﺷ
. ﯽـﻣ ﻦﯿﻣﺄـﺗ ار ﺎـﯿﻧد مدﺮﻣ زا ﯽﻤﯿﻧ زا ﺶﯿﺑ ﯽﻠﺻا ياﺬﻏ ﺞﻧﺮﺑ رد و ﺪـﻨﮐ
ﻦﯿﻣﺄﺗ ﺎﯿﺳآ هرﺎﻗ زا ﯽﻤﯿﻈﻋ ﺶﺨﺑ زا ﺶﯿﺑ هﺪﻨﻨﮐ
80 و يﺮﻟﺎﮐ ﺪﺻرد 75
ﺳا مدﺮﻣ ﯽﻓﺮﺼﻣ ﻦﯿﺌﺗوﺮﭘ ﺪﺻرد ﺖ
)
Agahi et al., 2012
(.
سﺎـﺳاﺮﺑ
زا ﺞﻧﺮـﺑ ﯽﻧﺎـﻬﺟ ﺪـﯿﻟﻮﺗ ناﺰﯿﻣ ﻮﺋﺎﻓ شراﺰﮔ 599
ﻠﯿﻣ ـﯿ لﺎـﺳ رد ﻦـﺗ نﻮ
2000 زا ﺶﯿﺑ ﻪﺑ يدﻼﯿﻣ 699
ﻠﯿﻣ ﯿ لﺎﺳ رد ﻦﺗ نﻮ 2010
ﺖﺳا هﺪﯿﺳر .
زا ناﺮﯾا رد ﺞﻧﺮﺑ ﺪﯿﻟﻮﺗ ناﺰﯿﻣ تﺪﻣ ﻦﯾا رد 97
/1 ﻪـﺑ ﻦـﺗ نﻮﯿﻠﯿﻣ 29
/2 .(FAOSTAT, 2010) ﺖﺳا هﺪﯿﺳر ﻦﺗ نﻮﯿﻠﯿﻣ ﺑ يرﺎﻤﯿ هدﺮﺘﺴﮔ زا ﯽﮑﯾ ﺖﺳﻼﺑ بﺮﺨﻣ و ﻦﯾﺮﺗ
يرﺎـﻤﯿﺑ ﻦﯾﺮﺗ يﺎـﻫ
ﻪﻤﯿﻧ و يﺮﯿﺴﻣﺮﮔ ﻖﻃﺎﻨﻣ رد ﺞﻧﺮﺑ ﯽﭼرﺎﻗ ﯽـﻣ بﻮﻃﺮﻣ يﺮﯿﺴﻣﺮﮔ
ﺪـﺷﺎﺑ
1 - ناﺮﯾا ،ﺖﺷر ،نﻼﯿﮔ هﺎﮕﺸﻧاد ،يزروﺎﺸﮐ نﻮﯿﺳاﺰﯿﻧﺎﮑﻣ هوﺮﮔ رﺎﯾدﺎﺘﺳا
*) - لﻮﺌﺴﻣ هﺪﻨﺴﯾﻮﻧ :
Email: [email protected] (
2 - ياﺮﺘﮐد يﻮﺠﺸﻧاد هوﺮﮔ
ﻢﺘﺴﯿﺳﻮﯿﺑ ﯽﺳﺪﻨﻬﻣ
، ناﺮﯾا ،زاﺮﯿﺷ ،زاﺮﯿﺷ هﺎﮕﺸﻧاد
3 - ﺸﻧاد رﺎﯿ هوﺮﮔ ناﺮﯾا ،زاﺮﯿﺷ ،زاﺮﯿﺷ هﺎﮕﺸﻧاد ،ﻢﺘﺴﯿﺳﻮﯿﺑ ﯽﺳﺪﻨﻬﻣ
ﯽــﻨﻌﻣ ﺶﻫﺎــﮐ ﺐﺒــﺳ ﻪــﮐ دراد يﺪــﯿﻟﻮﺗ لﻮــﺼﺤﻣ ناﺰــﯿﻣ رد يراد
)
Moumeni et al., 2003
.(
ﻪـﮐ هﺎﯿﮔ زا ﯽﺸﺨﺑ سﺎﺳاﺮﺑ يرﺎﻤﯿﺑ ﻦﯾا
ﺗ ﺖﺤﺗ ﺄ ﯽﻣ راﺮﻗ ﺮﯿﺛ مﺎﻧ ﻪﺑ دﺮﯿﮔ
،گﺮـﺑ ﺖـﺳﻼﺑ يﺎﻫ و ﻪـﺷﻮﺧ ﺖـﺳﻼﺑ
مﺎﻧ ندﺮﮔ ﯽﮔﺪﯿﺳﻮﭘ ﺖﺳﻼﺑ ﯽﻣ يراﺬﮔ
دﻮﺷ )
Gomathinayagam et
al., 2009
.(
ﻪﺑ يرﺎﻤﯿﺑ ﻢﯾﻼﻋ گﺮﺑ يور رد ﻪﮑﻟ ترﻮﺻ
ﺎـﺑ ﯽﮐود يﺎﻫ
هﻮـﻬﻗ ﻪﯿـﺷﺎﺣ و ﺪﯿﻔﺳ ﻪﺑ ﻞﯾﺎﻣ يﺮﺘﺴﮐﺎﺧ ﺰﮐﺮﻣ هﻮـﻬﻗ ﺎـﺗ يا
ﺰـﻣﺮﻗ يا
ﯽﻣﺮﻫﺎﻇ ﺪﻧدﺮﮔ ) ﻞﮑﺷ 1 - (.A
هﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ يرﺎﻤﯿﺑ ﻦﯾﺮﺘﻤﻬﻣ زا يا
يﺎﻫ ﺖـﺳا ﺞﻧﺮـﺑ ﯽﭼرﺎﻗ
ﻪﻠﻤﺣ درﻮﻣ ار لﻮﺼﺤﻣ ،ﻪﻋرﺰﻣ ﺎﺗ ﻪﻧاﺰﺧ زا هﺎﯿﮔ ﺪﺷر ﻞﺣاﺮﻣ ﻪﯿﻠﮐ رد ﻪﮐ ﯽـﻣ راﺮـﻗ ﺪـﻫد )
Bhattacharry and Mukhopudhyay, 1986
.(
ﻪﺑ يرﺎﻤﯿﺑ ﻢﺋﻼﻋ ﻪﮑﻟ ترﻮﺻ
هﻮﻬﻗ يﺎﻫ ﺎﺑ ﯽﻫﺎﮔ ،ﮓﻧر يا ﻫ
ﻪﻟﺎ ،درز يﺎﻫ
ماﺪـﻧا ﺮﺘﺸﯿﺑ يور ﻪﺘﺳﻮﯿﭘ ﻢﻫ ﻪﺑ ﺎﺗ دﺮﻔﻨﻣ ،يﻮﻀﯿﺑ ﺎﺗ دﺮﮔ ﯽﯾاﻮـﻫ يﺎـﻫ
ﯽـﻣ ﺮﻫﺎـﻇ ﻪﭽﻠﺒﻨـﺳ و ﻞﺒﻨﺳ ،ﻪﺷﻮﺧ ،گﺮﺑ ﻞﺜﻣ ﺪﻧﻮـﺷ
) Ou, 1985
.( B- 1 ﻞﮑﺷ
نﺎـﺸﻧ ﺞﻧﺮـﺑ هﺎـﯿﮔ گﺮـﺑ يور ﺮـﺑ ار يرﺎـﻤﯿﺑ ﻦﯾا ﻢﯾﻼﻋ
ﯽﻣ ﺪﻫد .
ﺞﻧﺮﺑ گﺮﺑ ياهﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ (B، ﺞﻧﺮﺑ گﺮﺑ ﺖﺳﻼﺑ يرﺎﻤﯿﺑ (A- 1 ﻞﮑﺷ
Fig.1. A) Rice blast disease, B) Rice brown spot disease
ﻪﻨﯾﺰﻫ ﻪﺑ ﻪﺟﻮﺗ ﺎﺑ
نﺎﯾز ﯽﻄﯿﺤﻣ ﺖﺴﯾز تاﺮﺛا و ﻻﺎﺑ يﺎﻫ ،مﻮﻤﺳ روآ
هدﺎﻔﺘﺳا ﻪﻓﺮﺻ و ﻖﯿﻗد ﯽﺗرﺎﻈﻧ شور ﮏﯾ زا يروﺮـﺿ نﺎﻣز رد هﺪﻨﻨﮐﻮﺟ
ﺖﺳا )
Bock et al., 2010; Steddom et al., 2005
.(
ًﺎﻣﻮﻤﻋ شور
ﺎﺑ هﺪﻫﺎﺸﻣ ﻏ ﻢﺸﭼ
ﯿﺮ اﺮﺑ ﺢﻠﺴﻣ ي ﻌﺗ ﯿﯿ ﻦ ﺑﯿ رﺎﻤ ي ـﻣ هدﺎﻔﺘﺳا ﯽ
دﻮـﺷ ﺎـﻣا
ﺎﺘﻧ ﯾ ﺞ ﻪﺑ هﺪﻣآ ﺖﺳد ﻪﺑ ﻪﺘﺴﺑاو
ﻦﻫذ مﺎـﺠﻧا ﺺﺨﺷ هدﻮـﺑ رﺎـﮐ هﺪـﻨﻫد
و
هزاﺪﻧا ﮔ ﯿﺮ ﻖـﯿﻗد ي ﻣ ـﯿ ناﺰ شﺮﺘـﺴﮔ ﺑﯿ رﺎـﻤ ي نﺎـﮑﻣا ﺬـﭘ ﯾﺮ ـﻤﻧ ﯽ ﺪـﺷﺎﺑ
)
Sanjay et al., 2011
.(
مواﺪــﻣ ترﺎــﻈﻧ ﻪــﺑ زﺎـﯿﻧ ﺮــﮕﯾد يﻮــﺳ زا
ﺖﻗو گرﺰﺑ عراﺰﻣ رد ﻪﮐ ﺖﺳا ﺮﻣا نﺎﺳﺎﻨﺷرﺎﮐ ﺪـﻫاﻮﺧ ﻪـﻨﯾﺰﻫ ﺮﭘ و ﺮﯿﮔ
دﻮﺑ . شور ﯽﺳرﺮﺑ ﻦﯾاﺮﺑﺎﻨﺑ ياﺮـﺑ ﻖـﯿﻗد و نازرا ،رﺎـﮐدﻮﺧ ،ﻊﯾﺮـﺳ يﺎﻫ
يرﺎــﻤﯿﺑ ﺺﯿﺨــﺸﺗ ا رادرﻮــﺧﺮﺑ يدﺎــﯾز ﺖــﯿﻤﻫا زا هﺎــﯿﮔ يﺎــﻫ
ﺖــﺳ
)
Camargo and Smith, 2009
.(
ﯽـﻣ ﯽـﻘﯿﻘﺤﺗ ﻦﯿـﻨﯿﭼ ﺞﯾﺎﺘﻧ ﺪـﻧاﻮﺗ
ﻪﺑ گرﺰﺑ عراﺰﻣ ﺶﯾﺎﭘ ياﺮﺑ ﺺﯿﺨـﺸﺗ رﺎـﮐدﻮﺧ و ﻊﯾﺮﺳ ﺺﯿﺨﺸﺗرﻮﻈﻨﻣ
ﻪﻧﺎﺸﻧ و ﻢﺋﻼﻋ ﺮﻫﺎـﻇ گﺮـﺑ يور ﺮـﺑ ﻪـﮑﻨﯾا ﺾـﺤﻣ ﻪـﺑ يرﺎـﻤﯿﺑ يﺎﻫ
ﯽﻣ ﻪﺑ ﺪﻧﻮﺷ دور رﺎﮐ )
Al-Bashish et al., 2011
.(
لﺎـﺘﯿﺠﯾد ﺮﯾﻮـﺼﺗ شزادﺮـﭘ ـﮐ ﺖـﺳا بﺮـﺨﻣ ﺮـﯿﻏ ﯽـﺷور ،1
ﺎــﺑ ﻪ
ﻪﺑ ﻊـﻤﺟ ياﺮﺑ دﻮﺟﻮﻣ تاﺰﯿﻬﺠﺗ يﺮﯿﮔرﺎﮐ ،ﻦﯿـﺑرود ﺪـﻨﻧﺎﻣ ﺮﯾﻮـﺼﺗ يروآ
ﻪﻣﺎﻧﺮﺑ و ﺮﻨﮑﺳا ،ﺮﺗﻮﯿﭙﻣﺎﮐ ﯽﻣ ﺮﯾوﺎﺼﺗ ﻞﯿﻠﺤﺗ و ﻪﯾﺰﺠﺗ يﺎﻫ
ﺮﯾوﺎـﺼﺗ ﺪﻧاﻮﺗ
زا جﺮﺨﺘـﺴﻣ تﺎـﻋﻼﻃا ﻞﯿﻠﺤﺗ و ﻪﯾﺰﺠﺗ ﻪﺑ و هدﻮﻤﻧ شزادﺮﭘ و ﻂﺒﺿ ار دزادﺮﭙﺑ ﺮﯾوﺎﺼﺗ )
Aglave at al., 2012
.(
زا هدﺎﻔﺘـﺳا نﺎـﮑﻣا ﯽـﺳرﺮﺑ
ﻪﻨﯿﻣز رد يزروﺎﺸﮐ رد ﺮﯾﻮﺼﺗ شزادﺮﭘ يژﻮﻟﻮﻨﮑﺗ نﻮـﭼ ﯽـﻔﻠﺘﺨﻣ يﺎﻫ
،لﻮـﺼﺤﻣ ﯽﮔﺪﯿـﺳر نﺎﻣز ﻦﯿﻤﺨﺗ ،تﻻﻮﺼﺤﻣ بﻮﻠﻄﻣ ﺪﺷر ﺮﺑ ترﺎﻈﻧ ﻦﯿﺷﺎﻣ ﺖﻓآ و زﺮﻫ ﻒﻠﻋ ﻦﯿﺟو يﺎﻫ ﺶﮐ
ﻪـﻗﻼﻋ درﻮـﻣ تﺎﻋﻮﺿﻮﻣ زا ﺎﻫ
لﺎـﺳ رد نﺎﻘﻘﺤﻣ ﺖـﺳا هدﻮـﺑ ﺮـﯿﺧا يﺎـﻫ
)
Hemming and Rath,
2001; Chen et al., 2002; Wang et al., 2002; Onyango,
.(2003
ﯽﻣ نﺎﺸﻧ تﺎﻌﻟﺎﻄﻣ ﯽﻣ ﻪﮐ ﺪﻫد
ﺮﯾﻮﺼﺗ شزادﺮﭘ ﮏﯿﻨﮑﺗ زا ناﻮﺗ
ﻪﺑ يرﺎﻤﯿﺑ ﺺﯿﺨﺸﺗ رد ﺖﯿﻘﻓﻮﻣ رﻮﻃ
دﻮـﻤﻧ هدﺎﻔﺘﺳا يﺰﯿﻣآ )
El-Hally
et al., 2008
.(
،ﺎﯾﻮﻣ ،ﺰﻧﻮﺒﯾر و ﺰﯿﺋﻮﺑ و اوﺪﻠﮑﺳا
نﺎﺸﻧارﺎﮑﻤﻫ )
Boese,
and Robbins, 2008; Moya et al., 2005; Skaloudova et al., 2006
( ﻪﺑ ﻪﻨﯿﻣز رد ﺐﯿﺗﺮﺗ گﺮـﺑ رد هدراو تﺎﻣﺪـﺻ ﺺﯿﺨﺸﺗ يﺎﻫ
1- Digital image processing
ﯽﻫﺎﻣرﺎﻣ ﻒﻠﻋ ﯽﯾﺎﯾرد هﺎﯿﮔ يردﻮـﭘ ﮏـﭙﮐ ﺺﯿﺨـﺸﺗ ،2
وﺪـﮐ هﺎـﯿﮔ3
و
زا ﯽــﺷﺎﻧ گﺮــﺑ ﺮــﺑ هدراو ترﺎــﺴﺧ ﻦﯿــﻤﺨﺗ مﺮــﮐ
ﯽﺗﻮــﺒﮑﻨﻋ يﺎــﻫ زا4
ﻪـﺑ ﺮﯾﻮـﺼﺗ شزادﺮﭘ و ﯽﯾﺎﻨﯿﺑ ﻦﯿﺷﺎﻣ يژﻮﻟﻮﻨﮑﺗ ﺖـﯿﻘﻓﻮﻣ رﻮـﻃ
يﺰـﯿﻣآ
هدﺎﻔﺘﺳا ﺪﻧدﻮﻤﻧ . ﻖﯿﻘﺤﺗ ﻦﯾا مﺎﺠﻧا زا فﺪﻫ ﺳرﺮﺑ
ﺮﯾﻮـﺼﺗ شزادﺮﭘ ﮏﯿﻨﮑﺗ ﯽﯾﺎﻧاﻮﺗ ﯽ
رد ﺨﺸﺗ ﯿ ﺺ يرﺎﻤﯿﺑ هﻮﻬﻗ ﻪﮑﻟ و ﺞﻧﺮﺑ ﺖﺳﻼﺑ يﺎﻫ ﯽـﻣ ﺞﻧﺮـﺑ يا
ﺪـﺷﺎﺑ
.يﺎﻫﯽ ﮔﮋﯾو جاﺮﺨﺘﺳا نﺎﮑﻣاﯽﺳرﺮﺑ ﺶﻫوﮋﭘ ﻦﯾا فﺪﻫ ،ﺮﮕﯾد ترﺎﺒﻋﻪﺑ ﮕﻧر و ﯽ ﻠﮑﺷ ﯽ وﺎﺼﺗ زا ﯾﺮ ﺰـﯿﻧ و ﺒﺗ نﺎـﮑﻣا ﯿـﯿ ﻦ و ﯾ ـﮔﮋ ﯽ يﺎـﻫ ﺮﻫﺎـﻇ ي
ﺑﻪ رﻮﮕﻟا ترﻮﺻ ﯾ
ﻢﺘ ﻫ ﺎ ي ﺷ ﺮﮔﺎﺳﺎﻨ ﺖﺳا ﺞﻧﺮﺑ گﺮﺑ ﺢﻄﺳ يرﺎﻤﯿﺑ عﻮﻧ .
شور و داﻮﻣ ﺎﻫ
ﻊﻤﺟ ﻪﻧﻮﻤﻧ يروآ ﺮﯾوﺎﺼﺗ ﻪﯿﻬﺗ و ﺎﻫ
ﺖـﺸﻟ ﺶـﺨﺑ ﺞﻧﺮـﺑ عراﺰـﻣ ﺢﻄـﺳ زا يﺪﯾدزﺎﺑ ﯽﻃ ﺎـﺸﻧ
ﻊـﺑاﻮﺗ زا ء
لﺎﺳ دادﺮﻣ ﻞﯾاوا رد ﺖﺷر نﺎﺘﺳﺮﻬﺷ 1391
ﻪﻧﻮﻤﻧ ،ﺖﻓﺮﮔ ترﻮﺻ يﺎـﻫ
يرﺎﻤﯿﺑ ﻪﺑ هدﻮﻟآ ﺞﻧﺮﺑ گﺮﺑ هﻮﻬﻗ ﻪﮑﻟ يﺎﻫ
ﻊﻤﺟ ﺞﻧﺮﺑ ﺖﺳﻼﺑ و يا يروآ
ﻪﻧﻮﻤﻧ ﺮﯾوﺎﺼﺗ ،ﺮﻨﮑﺳا ﮏﯾ زا هدﺎﻔﺘﺳا ﺎﺑ ﺲﭙﺳ و هﺪﺷ حﻮـﺿو ﺎﺑ ﺎﻫ
800
ﺖﻣﺮﻓ وdpi
ﺪﯾدﺮﮔ ﻪﯿﻬﺗJPEG
.
ﺮﯾوﺎﺼﺗ شزادﺮﭘ
شزادﺮـﭘ راﺰـﺑا ﻪـﺒﻌﺟ ﻪﺑ ﺮﯾﻮﺼﺗ شزادﺮﭘ ﺖﻬﺟ هﺪﺷ ﻪﯿﻬﺗ ﺮﯾوﺎﺼﺗ ﺪﻧﺪﺷ هداد لﺎﻘﺘﻧا ﺐﻠﺘﻣ راﺰﻓا مﺮﻧ ﺮﯾﻮﺼﺗ .
ﺗ ﻪﺑ ﻪﺟﻮﺗ ﺎﺑ ﺄ
يرﺎـﻤﯿﺑ دﺎﯾز ﺮﯿﺛ
هﺎﯿﮔ گﺮﺑ ﺢﻄﺳ ﮓﻧر يور ﺮﺑ ﮓـﻧر رﺎﮑـﺷآ توﺎـﻔﺗ هﺪﻫﺎﺸﻣ ﺎﺑ و ﺞﻧﺮﺑ
ﺖﻤﺴﻗ ﻦﯿﺑ ﺐﯿﺳآ و ﻢﻟﺎﺳ يﺎﻫ
ﯽـﮕﻧر شزادﺮـﭘ ﺖﯿﻠﺑﺎﻗ اﺪﺘﺑا ،گﺮﺑ هﺪﯾد
ﺖﻤﺴﻗ ﺺﯿﺨﺸﺗ ﺖﻬﺟ ﺮﯾوﺎﺼﺗ درﻮـﻣ گﺮـﺑ ﺢﻄـﺳ رﺎـﻤﯿﺑ و ﻢﻟﺎﺳ يﺎﻫ
ﺖﻓﺮﮔ راﺮﻗ ﯽﺳرﺮﺑ .
ﺮـﯾز ﻞـﺣاﺮﻣ ﻞﻣﺎﺷ ﺮﯾوﺎﺼﺗ ﯽﮕﻧر شزادﺮﭘ تﺎﯿﻠﻤﻋ
دﻮﺑ :
2- Eelgrass
3- Powdery mildew 4- Spider mites
) (A )
(B
ﺮﯾﻮﺼﺗ شزادﺮﭘ ﻒﻠﺘﺨﻣ ﻞﺣاﺮﻣ ترﺎﭼﻮﻠﻓ-2 ﻞﮑﺷ
Fig.2. Flowchart for several steps of image processing
ﯽﮕﻧر يﺎﻀﻓ ﻞﯾﺪﺒﺗ
ﻪـﮐ ﺖـﺳا ﯽﻤﺘﯾرﻮـﮕﻟا ﻪـﺑ ﯽﺑﺎﯿﺘـﺳد ﯽﮕﻧر يﺎﻀﻓ ﻞﯾﺪﺒﺗ زا فﺪﻫ ﺪـﻨﮐ ﺖﯾﻮﻘﺗ ﯽﯾﻻﺎﺑ ﺖﻗد ﺎﺑ ﺮﯾوﺎﺼﺗ رد ار يرﺎﻤﯿﺑ ﻢﯾﻼﻋ .
ﯽﯾﺎـﻬﻧ ﺖـﻗد
ﺘﯾرﻮﮕﻟا ﻪﻘﺒﻃ و ﺺﯿﺨﺸﺗ رد ﻢ يﺎـﻀﻓ ﻪـﺑ يدﺎـﯾز ﺪـﺣ ﺎﺗ يرﺎﻤﯿﺑ يﺪﻨﺑ
دراد ﯽﮕﺘﺴﺑ هﺪﺷ بﺎﺨﺘﻧا ﯽﮕﻧر .
ﯽﮕﻧر يﺎﻀﻓ ﺮﺑ هوﻼﻋ ﻖﯿﻘﺤﺗ ﻦﯾا رد
)RGB
ﯽـﮕﻧر يﺎﻀﻓ ﻦﯾا رد گﺮﺑ ﺢﻄﺳ زا هﺪﺷ ﻪﯿﻬﺗ ﻪﯿﻟوا ﺮﯾوﺎﺼﺗ ﻪﮐ ﺪﻧدﻮﺑ ( ﻪﻔﻟﺆﻣ ، ﯽـﮕﻧر يﺎـﻀﻓ رد ﯽـﮕﻧر يﺎﻫ HSI 1
ﻦﯿـﯿﻌﺗ ياﺮـﺑ ﺰـﯿﻧ
ﺖﻤـﺴﻗ ﻪـﺟو ﻦﯾﺮﺘﻬﺑ ﻪﺑ ﺪﻧاﻮﺘﺑ ﻪﮐ ﯽﮕﻧر ﻪﻔﻟﺆﻣ ﻦﯾﺮﺘﻬﺑ ار رﺎـﻤﯿﺑ يﺎـﻫ
ﺖﻓﺮﮔ راﺮﻗ ﯽﺳرﺮﺑ درﻮﻣ ﺪﯾﺎﻤﻧ ﻪﺘﺴﺟﺮﺑ .
ﻪﻔﻟﺆﻣ يﺎﻫ ،H وS ﯽـﮕﻧر سﻼـﮐ ردI ﻪـﺑHSI
ﺮﮕﻧﺎـﺸﻧ ﺐـﯿﺗﺮﺗ
ﺪﻨﺘﺴﻫ تﺪﺷ و عﺎﺒﺷا ،ﮓﻧر ﻞﺿﺎﻔﺗ ﺮﯾدﺎﻘﻣ .
1- Hue, Saturation and Intensity ﺶﺨﺑ
ﺮﯾوﺎﺼﺗ يﺪﻨﺑ ﻞﮑـﺷ رد ﺮﯾﻮـﺼﺗ شزادﺮﭘ ﻒﻠﺘﺨﻣ ﻞﺣاﺮﻣ ترﺎﭼﻮﻠﻓ 2
هداد نﺎـﺸﻧ
ﺖﺳا هﺪﺷ . ﻪـﺑ ﻪـﯿﻟوا ﺮﯾﻮﺼﺗ ﻞﯾﺪﺒﺗ ﻂﺳﻮﺗ ﺮﯾﻮﺼﺗ ﻪﻨﯿﻣز زا گﺮﺑ ﺢﻄﺳ اﺪﺘﺑا رد
ﺐﺳﺎﻨﻣ ﻪﻧﺎﺘﺳآ ﺪﺣ ﯽﻟﺎﻤﻋا و يﺮﺘﺴﮐﺎﺧ ﺮﯾﻮﺼﺗ ﺪﺷ يزﺎﺳاﺪﺟ
. ﯽـﻓﺮﻃ زا
ﻪـﻔﻟﺆﻣ ﯽـﺳرﺮﺑ ﺎﺑ يﺎـﻀﻓ ود رد ﯽـﮕﻧر ﻒـﻠﺘﺨﻣ يﺎـﻫ
وRGB HSV
ﺖﻤﺴﻗ ﻦﯿﺑ يرﺎﮑﺷآ توﺎﻔﺗ ﻪﮐ ﺪﺷ ﺺﺨﺸﻣ ﺢﻄـﺳ هدﻮـﻟآ و ﻢﻟﺎﺳ يﺎﻫ
ﯽﮕﻧر ﻪﻔﻟﺆﻣ رد گﺮﺑ دراد دﻮﺟوH
. ياﺮـﺑ قﻮـﻓ ﯽﮕﻧر ﻪﻔﻟﺆﻣ زا ﻦﯾاﺮﺑﺎﻨﺑ
ﺶﺨﺑ ﺪﺷ هدﺎﻔﺘﺳا ﺮﯾﻮﺼﺗ يﺪﻨﺑ .
لﺎﻤﻋا ﺎﺑ ﺮﯾﻮـﺼﺗ ﻦﯿـﺑ ﯽـﻘﻄﻨﻣAND
ﻪﻔﻟﺆﻣ ﺮﯾﻮﺼﺗ و ﻞﺒﻗ ﺖﻤﺴﻗ ﺪﯿﻔﺳ و هﺎﯿﺳ
،H
ﺖـﻬﺟ ﺮـﻈﻧ درﻮـﻣ ﺮﯾﻮﺼﺗ
ﻪﺑ ﯽﮕﻧر شزادﺮﭘ ﺎﺑ ﺮﺑاﺮﺑ ﺮﯾﻮﺼﺗ ﻪﻨﯿﻣز ﺮﯾدﺎﻘﻣ نآ رد ﻪﮐ ﺪﻣآ ﺖﺳد
ﺮﻔﺻ ﺶ ﯿـﭘ . دﻮـﺑ ﯽـﮕﻧر راﺪـﻘﻣ يراد گﺮﺑ ﺢﻄﺳ ﺎﻬﻨﺗ و ﺪﻧدﻮﺑ و ﺶﯾاﺰـﻓا زا
ﻞﺻﺎﺣ ﺮﯾﻮﺼﺗ ﯽﯾﺎﻨﺷور دﻮﺒﻬﺑ )
ﻪﺑ طﺎـﻘﻧ ﻦﯿـﺑ ﺰﯾﺎﻤﺗ ندﺮﮐ ﺮﺘﺸﯿﺑ رﻮﻈﻨﻣ
طﺎﻘﻧ ﯽﻗﺎﺑ زا ﻪﮑﻟ (
تﺪﺷ ماﺮﮔﻮﺘﺴﯿﻫ ، ﻪـﻔﻟﺆﻣ ﺮﯾﻮـﺼﺗ ﯽﮕﻧر ﺮﯾدﺎﻘﻣ يﺎﻫ
ﺪﺷ ﻢﺳر قﻮﻓ ﯽﮕﻧر )
ﻞﮑﺷ 3 ( ﺐـﺳﺎﻨﻣ ﻪﻧﺎﺘﺳآ ﺪﺣ راﺪﻘﻣ زا هدﺎﻔﺘﺳا ﺎﺑ و ﻪﺑ ﺎﺑ و
ﮐ ﻮﺴﺗوا شور يﺮﯿﮔرﺎ )
Otsu, 1979
( ﺐﯿـﺳآ طﺎﻘﻧ ﺢﻄـﺳ هﺪـﯾد
ﺪﺷ اﺪﺟ ﻢﻟﺎﺳ طﺎﻘﻧ زا گﺮﺑ .
H ﯽﮕﻧر ﻪﻔﻟﺆﻣ ﯽﮕﻧر تﺪﺷ ماﺮﮔﻮﺘﺴﯿﻫ- 3 ﻞﮑﺷ
Fig.3. Histogram of H color component intensities
ياﺮﺑ ﯽﮑﯾژﻮﻟﻮﻓرﻮﻣ تﺎﯿﻠﻤﻋ يرﺎﻤﯿﺑ عﻮﻧ ﺺﯿﺨﺸﺗ
هﻮـﻬﻗ ﻪـﮑﻟ يرﺎـﻤﯿﺑ ود ﯽـﮕﻧر ﺖﻫﺎﺒـﺷ ﻪﺑ ﻪﺟﻮﺗ ﺎﺑ ،ﺖـﺳﻼﺑ و يا
ﻪﺑ ﯽﻠﮑـﺷ شزادﺮـﭘ زا يرﺎـﻤﯿﺑ عﻮﻧ ود ﻦﯾا ﺰﯾﺎﻤﺗ رﻮﻈﻨﻣ ﺪـﺷ هدﺎﻔﺘـﺳا
.
ﻪﺑ ﻪﮑﻟ هزاﺪﻧا ﯽﻠﮐ رﻮﻃ يرﺎـﻤﯿﺑ ﻢـﺋﻼﻋ زا ﺮﺘﮔرﺰﺑ ﺖﺳﻼﺑ زا ﻞﺻﺎﺣ يﺎﻫ
هﻮﻬﻗ ﻪﮑﻟ شور ﻦـﯾا ،يرﺎـﻤﯿﺑ ﻦـﺳ توﺎـﻔﺗ ﻪـﺑ ﻪـﺟﻮﺗ ﺎـﺑ ﺎﻣا ﺖﺳا يا
ﯽﻤﻧ ﻮﺗ ﻪﮑﻟ هزاﺪﻧا اﺮﯾز ﺪﺷﺎﺑ ﯽﺒﺳﺎﻨﻣ رﺎﯿﻌﻣ ﺪﻧا رد ﺖـﺳﻼﺑ زا ﻞـﺻﺎﺣ يﺎﻫ
ﯽﻣ يرﺎﻤﯿﺑ ﻦﯾا زوﺮﺑ ﻪﯿﻟوا ﻞﺣاﺮﻣ ﻪﮑﻟ ﺎﺑ ﺪﻨﻧاﻮﺗ
يرﺎـﻤﯿﺑ زا ﻪﻠـﺻﺎﺣ يﺎﻫ
هﻮﻬﻗ ﻪﮑﻟ ﺪﻨﺷﺎﺑ هزاﺪﻧا ﻢﻫ ﺮﺗﻻﺎﺑ ﺖﻓﺮﺸﯿﭘ ﻪﻠﺣﺮﻣ ﺎﺑ يا .
ﺎﻣا هﺪﻤﻋ توﺎﻔﺗ
ﺖﺳﻼﺑ يرﺎﻤﯿﺑ زا ﻞﺻﺎﺣ ﻢﺋﻼﻋ ﻪﮐ ﺖﺳا ﻦﯾا يرﺎﻤﯿﺑ ود ﻦﯾا ﻞﮑﺷ رد ﺮﺑ گﺮﺑ ﻪﺑ ﺞﻧ ﯽﮐود ترﻮﺻ هدﻮﺑ ﻞﮑﺷ
) ﻪﺷﻮﮔ و ﻦﻬﭘ ﻂﺳو رد كﻮﻧ يﺎﻫ
ﺰﯿﺗ ( هﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ زا ﻞﺻﺎﺣ ﻢﺋﻼﻋ ﺎﻣا ﻪﺑ ًﺎﻣﻮﻤﻋ يا
يوﺮـﯾاد ترﻮﺻ
ﯽﻣ راﺪﯾﺪﭘ هﺎﯿﮔ گﺮﺑ يور ﺮﺑ ﻞﮑﺷ ﯽﻀﯿﺑ ﯽﻫﺎﮔ و دﻮﺷ
)
Nithya and
Sundaram, 2011
.(
ﯽﮔﮋﯾو ﯽﻣ ار ﯽﻠﮑﺷ يﺎﻫ ﻪﺑ ناﻮﺗ
هزاﺪﻧا زا ﯽﺒﯿﮐﺮﺗ ﺎﯾ ﻞﻘﺘﺴﻣ ترﻮﺻ
دﺎﻌﺑا دﻮﻤﻧ ﺺﺨﺸﻣ .
ﺪـﻌﺑ نوﺪﺑ ﯽﻠﮑﺷ ﺖﯿﺻﻮﺼﺧ رﺎﻬﭼ ﻖﯿﻘﺤﺗ ﻦﯾا رد
ﻪﮑﻟ زا ﺮﯾز ﺪﻧﺪﺷ جاﺮﺨﺘﺳا يرﺎﻤﯿﺑ عﻮﻧ ود يﺎﻫ :
1يدﺮﮔ ) :(R
ﻪـﮑﻟ ﺮﯾوﺎـﺼﺗ يدﺮﮔ راﺪﻘﻣ لﻮـﻣﺮﻓ ﻪـﺑ ﻪـﺟﻮﺗ ﺎـﺑ ﺎـﻫ
هزاﺪﻧا هﺮـﯾاد ﺮﯿﻏ لﺎﮑﺷا رد يدﺮﮔ يﺮﯿﮔ ،يا
ﻪـﻄﺑار زا )1 ( ﺪـﺷ ﻦﯿـﯿﻌﺗ
)
Liu et al., 2005
.(
1- Roundness
= ( ⁄ ) ( )1 يﺮﻫﺎﻇ ﺖﺒﺴﻧ )2
AcR
:(
ﺮـﻄﻗ ﻪـﺑ ﻪﻨﯿـﺸﯿﺑ ﺮـﻄﻗ ﺖﺒﺴﻧ ﺎﺑ ﺮﺑاﺮﺑ ﻪﮐ
ﺖﺳا ءﯽﺷ ﻪﻨﯿﻤﮐ )
Liu et al., 2005
.(
= ( )2 ﯽﮔدﺮﺸﻓ )3
SF
:(
و ﻞﮑـﺷ ﯽﮔدﺮـﺸﻓ زا ﺖﺳا يرﺎﯿﻌﻣ ﻪـﻄﺑار زا
)3 (
ﺪﺷ ﻪﺒﺳﺎﺤﻣ )
Shouche et al., 2001
:(
= ( )3 ﺢﻄﺳ ﺖﺒﺴﻧ )4
AR
:(
ﺮـﻄﻗ بﺮﻀﻠﺻﺎﺣ ﻪﺑ ﺢﻄﺳ ﺖﺣﺎﺴﻣ ﺖﺒﺴﻧ ﻪﮐ
ﺖﺳا ﻪﻨﯿﻤﮐ و ﻪﻨﯿﺸﯿﺑ .
= × ( )4 ؛قﻮﻓ ﻂﺑاور رد ﻪﮐ ﺮﯾﻮﺼﺗ ﺢﻄﺳ ﺖﺣﺎﺴﻣA
) ﻪﺑ طﻮﺑﺮﻣ ﺪﯿﻔﺳ طﺎﻘﻧ
يﺮﻨﯾﺎﺑ ﺮﯾﻮﺼﺗ رد ﺮﻈﻧ درﻮﻣ ءﯽﺷ ( ،
DMax
و DMin
ﻪـﺑ ﺮﯾدﺎـﻘﻣ ﺐـﯿﺗﺮﺗ
و ﺮﯾﻮﺼﺗ رد ءﯽﺷ ﻪﻨﯿﻤﮐ و ﻪﻨﯿﺸﯿﺑ ﺮﻄﻗ رد ﺮـﻈﻧ درﻮـﻣ ءﯽـﺷ ﻂﯿﺤﻣP
ﯽﻣ يﺮﻨﯾﺎﺑ ﺮﯾﻮﺼﺗ ﺪﻨﺷﺎﺑ
.
عﻮـﻧ ود يزﺎـﺳاﺪﺟ ﺖـﻬﺟ ﯽﻠﮑـﺷ تﺎﯿـﺻﻮﺼﺧ ﻦﯾﺮﺘﻬﺑ ﺖﯾﺎﻬﻧ رد ﯽﻠﮑـﺷ تﺎﯿـﺻﻮﺼﺧ سﺎـﺳاﺮﺑ يرﺎﻤﯿﺑ عﻮﻧ ﺺﯿﺨﺸﺗ و بﺎﺨﺘﻧا يرﺎﻤﯿﺑ
2- Aspect ratio
3- Compactness 4- Area ratio
ﺪﺷ مﺎﺠﻧا قﻮﻓ .
ﺚﺤﺑ و ﺞﯾﺎﺘﻧ
ﻪﻔﻟﺆﻣ ﻞﯿﺴﻧﺎﺘﭘ ﻪﻌﻄﻗ رد ﮓﻧر يﺎﻫ
ﺮﯾوﺎﺼﺗ يﺪﻨﺑ
تﺪﺷ ﯽﮔﺪﻨﮐاﺮﭘ يﺎﻫرادﻮﻤﻧ ﻪـﻔﻟﺆﻣ يﺎﻫ
يﺎﻫﺎـﻀﻓ رد ﯽـﮕﻧر يﺎـﻫ ﯽﮕﻧر
وRGB
ﻞﮑﺷ ردHSV
4 هداد نﺎﺸﻧ ﻪـﺑ ﻪـﺟﻮﺗ ﺎـﺑ ،ﺖﺳا هﺪﺷ
ﺖﻤﺴﻗ ﻪﮐ ﺖﺳا ﺺﺨﺸﻣ ﻞﮑﺷ ﻪـﻔﻟﺆﻣ رد گﺮـﺑ هدﻮـﻟآ و ﻢﻟﺎـﺳ يﺎـﻫ
ﯽﮕﻧر ﺖـﺳا ﺐﻠﻄﻣ ﻦﯾا ﺪﯾﺆﻣ ﻪﮐ ﺪﻧراد ﺮﮕﯾﺪﻤﻫ زا ار ﺰﯾﺎﻤﺗ ﻦﯾﺮﺘﺸﯿﺑH
ﻪﮐ زا ﻪﻔﻟﺆﻣ ﻦﯾا
، يرﺎﻤﯿﺑ ﺺﯿﺨﺸﺗ ياﺮﺑ ﺞﯾﺎﺘﻧ ﻦﯾﺮﺘﻬﺑ ﺪـﻨﻫاﻮﺧ ﺞﺘﻨﻣ ﺎﻫ
ﺪﺷ .
ﻞﮑﺷ 4 ﻪﻔﻟﺆﻣ ﯽﮕﻧر ﺮﯾدﺎﻘﻣ ﯽﮔﺪﻨﮐاﺮﭘ رادﻮﻤﻧ - ﺖﻤﺴﻗ ياﺮﺑ ﻒﻠﺘﺨﻣ ﯽﮕﻧر يﺎﻫ
ﻪﮑﻟ و گﺮﺑ ﻢﻟﺎﺳ يﺎﻫ ﯽﮕﻧر يﺎﻀﻓ ،يرﺎﻤﯿﺑ زا ﻞﺻﺎﺣ يﺎﻫ
RGB
) (A
ﯽﮕﻧر يﺎﻀﻓ و
)HSV (B
Fig.4. Scatter plots of color components for leaf healthy and defected parts, RGB color space (A) and HSI color space (B)
) (A
) (B
ﻞﮑﺷ 5 - ؛گﺮﺑ ﺢﻄﺳ زا ﻪﮑﻟ ﺺﯿﺨﺸﺗ ﻒﻠﺘﺨﻣ ﻞﺣاﺮﻣ (A
،گﺮﺑ ﺢﻄﺳ ﻪﯿﻟوا ﺮﯾﻮﺼﺗ (B
و هﺎﯿﺳ ﺮﯾﻮﺼﺗ ،ﺮﯾﻮﺼﺗ ﻪﻨﯿﻣز زا گﺮﺑ يزﺎﺳاﺪﺟ ياﺮﺑ ﺪﯿﻔﺳ
(C
ﺮﯾﻮﺼﺗ ،ﻪﯿﻟوا ﺮﯾﻮﺼﺗ زا ﻞﺻﺎﺣHSV
(D
ﻪﻔﻟﺆﻣ ﺮﯾﻮﺼﺗ ،H
(E
تﺎﯿﻠﻤﻋ زا ﻞﺻﺎﺣ ﺮﯾﻮﺼﺗ ﻞﻤﮑﻣ ﺮﯾﻮﺼﺗ ﻦﯿﺑ ﯽﻘﻄﻨﻣAND
يﺮﻨﯾﺎﺑ ﺮﯾﻮﺼﺗ وH
ﺖﻤﺴﻗ ) ( ،B
(F
زا ﻞﺻﺎﺣ ﺮﯾﻮﺼﺗ ﺮﯾﻮﺼﺗ ﯽﯾﺎﻨﺷور دﻮﺒﻬﺑ و ﺶﯾاﺰﻓا تﺎﯿﻠﻤﻋ
) ( ،E
(G
ﯽﯾﺎﻬﻧ ﺪﯿﻔﺳ و هﺎﯿﺳ ﺮﯾﻮﺼﺗ
Fig.5. Several steps of stain recognition: A) Original color image of rice leaf, B) Binary image to segment leaf from background, C) HSI image, D) H color component image, E) The resulting image after performing a logical AND between complement of H and binary image of step (B), F) Adjusted image resulted from image of step (E), G) Final
segmented image
ﻣ ،ﺖـﺳا ﺺﺨﺸﻣ قﻮﻓ يﺎﻫرادﻮﻤﻧ زا ﻪﮐ رﻮﻄﻧﺎﻤﻫ ﯽـﮕﻧر ﻪـﻔﻟﺆ
H
ﺖﻤﺴﻗ ﻪﺑ طﻮﺑﺮﻣ گﺮﺑ ﻢﻟﺎﺳ يﺎﻫ
، ﺖﻤﺴﻗ زا ًﻼﻣﺎﮐ ﺰﯾﺎﻤﺘﻣ نآ رﺎﻤﯿﺑ يﺎﻫ
ﭻﯿﻫ ﺮﮕﯾد فﺮﻃ زا ،ﺖﺳا ﻪﻔﻟﺆﻣ زا ماﺪﮐ
ﺰﯾﺎـﻤﺗ هﺪـﺷ نﺎﺤﺘﻣا ﯽﮕﻧر يﺎﻫ هﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ ﻦﯿﺑ ﯽﻠﻣﺎﮐ
ﻪﺑ ار ﺞﻧﺮﺑ گﺮﺑ ﺖﺳﻼﺑ يرﺎﻤﯿﺑ يا ﺖـﺳد
ﯽﻤﻧ ﺪﻨﻫد .
(B) (A)
(G) (D) (C)
(F) (E)
لوﺪﺟ 1 ﯾدﺎﻘﻣ- ﯽﻠﮑﺷ تﺎﯿﺻﻮﺼﺧ ﺮ
Table 1- Values of shape characteristics ﯽﮔدﺮﺸﻓ
**
Compactness**
ﺢﻄﺳ ﺖﺒﺴﻧ
ns
Area rations
يدﺮﮔ
**
Roundness**
يﺮﻫﺎﻇ ﺖﺒﺴﻧ
**
Aspect ratio**
ﺖﺳﻼﺑ
Blast 0.42±0.027 0.75±0.029 0.28±0.019 0.29±0.022 هﻮﻬﻗ ﻪﮑﻟ
يا
Brown spot 0.89±0.026 0.78±0.027 0.71±0.023 0.71±0.024 :ns
ﯽﻨﻌﻣ توﺎﻔﺗ مﺪﻋ ،راد
:**
ﯽﻨﻌﻣ توﺎﻔﺗ لﺎﻤﺘﺣا ﺢﻄﺳ رد راد 1
%
ns: Corresponding to no significant difference, **: Corresponding to 1% probability
ﻞﮑﺷ 6 - (A
،ﺞﻧﺮﺑ گﺮﺑ ﺢﻄﺳ زا ﻪﯿﻟوا ﯽﮕﻧر ﺮﯾوﺎﺼﺗ (B
ﻪﺑ ﯽﯾﺎﻬﻧ ﺮﯾﻮﺼﺗ ﺞﻧﺮﺑ ﺖﺳﻼﺑ يرﺎﻤﯿﺑ ﺺﯿﺨﺸﺗ ﺖﻬﺟ هﺪﻣآ ﺖﺳد
) ﮓﻧر درز ﺖﻤﺴﻗ (
زا
هﻮﻬﻗ ﻪﮑﻟ يرﺎﻤﯿﺑ يا
) هﻮﻬﻗ ﺖﻤﺴﻗ ﮓﻧر يا
(
Fig.6. A) Original RGB images from rice leaf surface, B) Final image resulted to distinguish the rice blast disease (yellow parts) from brown spot disease (brown parts)
ﺶﺨﺑ ﺞﯾﺎﺘﻧ ﺮﯾوﺎﺼﺗ يﺪﻨﺑ
ﺶﺨﺑ ﻒﻠﺘﺨﻣ ﻞﺣاﺮﻣ ﻪﺑ طﻮﺑﺮﻣ ﺮﯾوﺎﺼﺗ ﻞﮑـﺷ رد ﺮﯾﻮـﺼﺗ يﺪﻨﺑ
5 . ﺖﺳا هﺪﺷ هداد نﺎﺸﻧ
ﯽﮕﻧﻮـﮕﭼ ﻪـﺑ طﻮـﺑﺮﻣ ﺮﯾﻮـﺼﺗ زا ﻪﮐ يرﻮﻄﻧﺎﻤﻫ
ﻪﻔﻟﺆﻣ زا هدﺎﻔﺘﺳا ﺎﺑ گﺮﺑ ﺢﻄﺳ زا ﻪﮑﻟ يزﺎﺳاﺪﺟ ﻞﮑـﺷ ردH
5 نﺎـﺸﻧ
هﺪﺷ هداد يرﺎـﻤﯿﺑ ﺺﯿﺨـﺸﺗ رد هﺪـﺷ ﻪﺋارا ﻢﺘﯾرﻮﮕﻟا ،ﺖﺳا ﻪـﮑﻟ يﺎـﻫ
هﻮﻬﻗ ﺖﺳا هدﻮﺑ ﻖﻓﻮﻣ ﺞﻧﺮﺑ گﺮﺑ ﺢﻄﺳ زا ﺞﻧﺮﺑ ﺖﺳﻼﺑ و يا .
ﺮﯾدﺎﻘﻣ ﺰﯿﻧ ﻢﺘﯾرﻮﮕﻟا ﺖﺴﺗ ياﺮﺑ وCCR
ﺪﻧﺪﺷ ﻪﺒﺳﺎﺤﻣMCR
: ﻪﺑ ﻪﮐ يرﺎﻤﯿﺑ ﻪﮑﻟ يﺎﻫﻞﺴﮑﯿﭘ داﺪﻌﺗ زا ﺖﺴﺗرﺎﺒﻋ :1CCR
ﯽﺘـﺳرد
ﺑﻪ هﺪﺷ ﻪﺘﻓﺮﮔ ﺮﻈﻧ رد ﻪﮑﻟ ناﻮﻨﻋ ﻞﮐ داﺪﻌﺗ ﻪﺑ ﺪﻧا
ﻞﺴﮑﯿﭘ ﻪﮑﻟ يﺎﻫ ﺎﻫ
. ﺖﻤﺴﻗ يﺎﻫﻞﺴﮑﯿﭘ داﺪﻌﺗ زا ﺖﺴﺗرﺎﺒﻋ :2MCR
گﺮـﺑ ﻢﻟﺎـﺳ يﺎـﻫ
ﻪـﺑ هﺎﺒﺘﺷا ﻪﺑ ﺪﯿﻔﺳ و هﺎﯿﺳ ﺖﻟﺎﺣ ﻪﺑ ﺮﯾﻮﺼﺗ ﻞﯾﺪﺒﺗ مﺎﮕﻨﻫ رد ﻪﮐ ناﻮـﻨﻋ
ﻪﮑﻟ هﺪﺷ ﻪﺘﻓﺮﮔ ﺮﻈﻧ رد يرﺎﻤﯿﺑ يﺎﻫ ﮐ داﺪﻌﺗ ﻪﺑ ﺪﻧا
ﻞﺴﮑﯿﭘ ﻞ ﺰﺒـﺳ يﺎـﻫ
) ﻢﻟﺎﺳ ﺖﻤﺴﻗ اﺪﺘﺑا ﻪﮐ دﻮﺑ ترﻮﺻ ﻦﯾا ﻪﺑ رﺎﮐ شور.(
ﺮـﻫ ﻪـﺑ طﻮـﺑﺮﻣ يﺎﻫ
1- Correct classification rate 2- Misclassification rate
ﺖﻤﺴﻗ زا ﮏﯾ ،ﻪـﺠﯿﺘﻧ ﺮﯾﻮـﺼﺗ يور زا گﺮـﺑ ﺢﻄـﺳ هدﻮﻟآ و ﻢﻟﺎﺳ يﺎﻫ
ﺑﻪ راﺰـﻓا مﺮـﻧ زا هدﺎﻔﺘـﺳا ﺎـﺑ ﯽﺘﺳد رﻮﻃ
Adobe Photoshop
ﻪﺨـﺴﻧ
ﺪﺷ اﺪﺟCS6
ﺑ. ﻪ ﻞﺴﮑﯿﭘ ﺐﯿﺗﺮﺗ ﻦﯿﻤﻫ ﺖﻤـﺴﻗ ﻪـﺑ طﻮـﺑﺮﻣ يﺎﻫ
يﺎـﻫ
ﻞﺴﮑﯿﭘ و گﺮﺑ ﺢﻄﺳ هدﻮﻟآ و ﻢﻟﺎﺳ ﺪـﯾدﺮﮔ شرﺎﻤـﺷ نآ ﻪﺑ طﻮﺑﺮﻣ يﺎﻫ
ﺑ ﺮﯾدﺎﻘﻣ ﻢﯿﺴﻘﺗ ﺎﺑ ﺲﭙﺳ ﻪ
هﺪـﻣآ ﺖـﺳد ﯽـﯾودود ﺮﯾوﺎـﺼﺗ زا
ﺮـﺑ ﻪـﺠﯿﺘﻧ
ﺑ ﺮﯾدﺎﻘﻣ ﻪ ،ﯽﻠﺻا ﺮﯾﻮﺼﺗ زا هﺪﻣآ ﺖﺳد
وCCR
ﺪـﺷ ﻪﺒﺳﺎﺤﻣMCR
.
ردCCR ﺮﯾدﺎـﻘﻣ ﺪﻧﺪـﺷ ﺶﯾﺎـﻣزآ ترﻮـﺻ ﻦﯾا ﻪﺑ ﻪﮐ يﺮﯾﻮﺼﺗ30 ﻦﯿﺑ و
ﺑMCR
ﻪ ﺎﺑ ﺮﺑاﺮﺑ ﺐﯿﺗﺮﺗ 8/
1 3/± 96 و ﺪﺻرد 9 /0 2/± 3 ﺑ ﺪﺻرد ﻪ ﺖﺳد
ﺪﻣآ . ﺎﺑ ﺮﺑاﺮﺑ يزﺎﺳاﺪﺟ ﺖﻗد 4/
1 4/± 97 ﻪﺑ ﻪﮐ ﺪﻣآ ﺖﺳد رﺎﯿـﺴﺑ ناﺰـﯿﻣ
ﯽﻣ ﯽﯾﻻﺎﺑ ﺪﺷﺎﺑ و ﺶـﺨﺑ رد هﺪﺷ ﻪﺋارا ﯽﮔﺪﻨﮐاﺮﭘ يﺎﻫرادﻮﻤﻧ ﻪﺑ ﻪﺟﻮﺗ ﺎﺑ
ﺶﯿﭘ ﻞﺑﺎﻗ مﻮﺳ دﻮﺑ ﯽﻨﯿﺑ
.
ﯽﻠﮑﺷ تﺎﯿﺻﻮﺼﺧ سﺎﺳاﺮﺑ يرﺎﻤﯿﺑ عﻮﻧ ﺺﯿﺨﺸﺗ
ﻪﺑ ﯽﻨﻌﻣ ﯽﺳرﺮﺑ رﻮﻈﻨﻣ يرﺎـﻤﯿﺑ عﻮـﻧ ود ﻦﯿﺑ ﯽﻠﮑﺷ توﺎﻔﺗ ندﻮﺑ راد
نﻮﻣزآ زا ﺪﺷ مﺎﺠﻧاt
. داﺪﻌﺗ زا 30 ﺮﻫ زا ﻪﻧﻮﻤﻧ ياﺮﺑ يرﺎﻤﯿﺑ عﻮﻧ
ﺖـﺴﺗ
لوﺪﺟ رد نآ ﺞﯾﺎﺘﻧ ﻪﮐ ﺪﯾدﺮﮔ هدﺎﻔﺘﺳا 1
ﺖـﺳا هﺪﺷ هداد نﺎﺸﻧ .
ﺞﯾﺎـﺘﻧ
) A (
) B (
ﺖﺒـﺴﻧ ﺎـﻬﻨﺗ هﺪﺷ جاﺮﺨﺘﺳا ﯽﮔﮋﯾو رﺎﻬﭼ ﻦﯿﺑ زا ﻪﮐ ﺖﺳا ﻦﯾا زا ﯽﮐﺎﺣ ﺮـﮕﯾد ﯽـﮔﮋﯾو ﻪـﺳ رد و ﺖـﺷاﺪﻧ ﯽﺗوﺎـﻔﺗ ﻢﻫ ﺎﺑ يرﺎﻤﯿﺑ عﻮﻧ ود ﺢﻄﺳ ﯽﻨﻌﻣ فﻼﺘﺧا لﺎﻤﺘﺣا ﺢﻄﺳ رد يراد
1 % يرﺎﻤﯿﺑ و ﺖﺳﻼﺑ يرﺎﻤﯿﺑ ﻦﯿﺑ
هﻮﻬﻗ ﻪﮑﻟ ﻫﺎﺸﻣ يا ﺪﺷ هﺪ .
طﺮﺷ بﺎﺨﺘﻧا ﺎﺑ ﺖﯾﺎﻬﻧ رد ﻪﻧﺎﺘـﺳآ دوﺪـﺣ لﺎـﻤﻋا و ﺐـﺳﺎﻨﻣ يﺎـﻫ
ﯽﮔﮋﯾو ﺮﯾدﺎﻘﻣ ﻦﯿﺑ ﺐﺳﺎﻨﻣ ﻢﺘﯾرﻮﮕﻟا ،قﻮﻓ لوﺪﺟ ﻪﺑ ﻪﺟﻮﺗ ﺎﺑ ﯽﻠﮑﺷ يﺎﻫ
ﺖﻤـﺴﻗ زا ﻞـﺻﺎﺣ ﺮﯾوﺎـﺼﺗ رد رد ار يرﺎـﻤﯿﺑ عﻮـﻧ ﺖـﺴﻧاﻮﺗ هﺪﺷ ﻪﺋارا ﻪﻌﻄﻗ زا ﺶﯿﺑ ﺖﻗد ﺎﺑ ،يﺪﻨﺑ 6/
96 % ﺪﻫد ﺺﯿﺨﺸﺗ .
ﻪـﮐ ترﻮﺻ ﻦﯾا ﻪﺑ
ﻦﯿﺑ زا 60 ﺎﻤﯿﺑ ﻪﻧﻮﻤﻧ ير ) 30 و ﺖـﺳﻼﺑ ﻪـﺑ طﻮـﺑﺮﻣ ﻪـﻧﻮﻤﻧ 30
ﻪـﻧﻮﻤﻧ
هﻮﻬﻗ ﻪﮑﻟ ﻪﺑ طﻮﺑﺮﻣ يا
( ﺖـﻓﺮﮔ راﺮﻗ ﻂﻠﻏ هوﺮﮔ رد درﻮﻣ ود ﺎﻬﻨﺗ .
ﻞﮑـﺷ
6 ﺮـﺑ ﻪﻧﺎﺘـﺳآ دوﺪـﺣ لﺎﻤﻋا و ﯽﻠﮑﺷ ﺰﯿﻟﺎﻧآ زا ﺲﭘ ﻪﻠﺻﺎﺣ ﯽﯾﺎﻬﻧ ﺮﯾﻮﺼﺗ
ﯽﮔﮋﯾو يور ﯽﻣ نﺎﺸﻧ ار ﯽﻠﮑﺷ يﺎﻫ
ﺪﻫد .
ﻪﺠﯿﺘﻧ
يﺮﯿﮔ
ﺺﯿﺨﺸﺗ رد ﺮﯾﻮﺼﺗ شزادﺮﭘ شور ﯽﯾﺎﻧاﻮﺗ ﻖﯿﻘﺤﺗ ﻦﯾا رد ﻦﯿﯿﻌﺗ و
هﻮـﻬﻗ ﻪـﮑﻟ و ﺖﺳﻼﺑ يرﺎﻤﯿﺑ ود عﻮﻧ درﻮـﻣ ﺞﻧﺮـﺑ گﺮـﺑ ﺢﻄـﺳ رد يا
زرا ﯾ ﺖﻓﺮﮔ راﺮﻗ ﯽﺑﺎ .
ﯽﻣ ﺮﯾﻮﺼﺗ شزادﺮﭘ شور ﻪﮐ داد نﺎﺸﻧ ﺞﯾﺎﺘﻧ ﺪـﻧاﻮﺗ
گﺮﺑ ﯽﯾﻻﺎﺑ ﺖﻗد ﺎﺑ گﺮﺑ زا ار ﻢﻟﺎﺳ يﺎﻫ
عﻮـﻧ و هدﻮـﻤﻧ اﺪـﺟ هدﻮﻟآ يﺎﻫ
ﺪﻫد ﺺﯿﺨﺸﺗ ﯽﯾﻻﺎﺑ ﺖﻗد ﺎﺑ ﺰﯿﻧ ار يرﺎﻤﯿﺑ .
ﯽﻣ ﺮﻈﻧ ﻪﺑ ﺳر
ﺪ يرﺎﻤﯿﺑ ﻪﮑﻨﯾا ﻪﺑ ﻪﺟﻮﺗ ﺎﺑ ـﺑ ﯽﻫﺎـﯿﮔ يﺎـﻫ
ﻪ ترﻮـﺻ
ﻪﻘﻄﻨﻣ ﯽﻣ عﻮﯿﺷ ﻪﻋرﺰﻣ رد يا ﯽﻣ ﺪﺑﺎﯾ
زا ناﻮﺗ و ﺮﯾﻮﺼﺗ شزادﺮﭘ ﮏﯿﻨﮑﺗ
ﻪﺑ ﯽﯾﺎﻨﯿﺑ ﻦﯿﺷﺎﻣ يژﻮﻟﻮﻨﮑﺗ يرﺎﻤﯿﺑ ﻦﯾا ﻊﻗﻮﻣ ﻪﺑ و ﻖﯿﻗد ﻦﯿﯿﻌﺗ رﻮﻈﻨﻣ
ﺎﻫ
ﻞﻗاﺪـﺣ ﻪـﺑ ار لﻮﺼﺤﻣ تﺎﻔﻠﺗ ناﺰﯿﻣ ﻪﮐ دﻮﻤﻧ هدﺎﻔﺘﺳا ﻪﻋرﺰﻣ ﺢﻄﺳ رد ﻪﺑ ﺎﺑ ﯽﻓﺮﻃ زا و هﺪﻧﺎﺳر ﺎﮐ
ﻪـﻘﻄﻨﻣ ﺖﯾﺮﯾﺪـﻣ يﺮﯿﮔر ﻦـﯾا ﻪـﺑ ﻪـﻋرﺰﻣ يا
ﯽﻣ شور ﺪﻧﺎﺳر ﻞﻗاﺪﺣ ﻪﺑ ار ﯽﯾﺎﯿﻤﯿﺷ داﻮﻣ ﻪﺑ زﺎﯿﻧ ناﺰﯿﻣ ناﻮﺗ .
References
1. Agahi, K., M. H. Fotokian, and Z. Younesi. 2012. Study of genetic diversity and important correlations of agronomic traits in rice genotypes (Oryza sativa L.). Iranian Journal of Biology 25 (1): 97-110. (In Farsi).
2. Aglave, V. A., S. B. Patil, and N. B. Sambre. 2012. Imaging technique to measure leaf area, disease severity and chlorophyll content: asurvey paper. Computing Technologies 1 (3).
3. Al-Bashish, D., M. Braik, and S. Bani-Ahmad. 2011. Detection and classification of leaf diseases using K-means-based segmentation and neural-networks-based classification. Information Technology Journal 10: 267-275.
4. Bock, C. H., G. H. Poole, P. E. Parker, and T. R. Gottwald. 2010. Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Critical Reviews in Plant Science 29: 59-107.
5. Boese, B. L., and B. D. Robbins. 2008. Effects of erosion and macroalgae on intertidal eelgrass (zostera marina) in a northeastern Pacific estuary (USA). Botanica Marina 51: 247-257.
6. Camargo, A., and J. S. Smith. 2009. An image-processing based algorithmtoautomatically identify plant disease visual symptoms. Biosystems Engineering 102 (1): 9-21.
7. Chen, Y. R., K. Chao, and S. K. Moon. 2002. Machine vision technology for agricultural applications.
Computers and Electronics in Agriculture 36 (2–3): 173-191.
8. El-Hally, M., A. Refea, S. Al-Gamal, and R. A. Al-Whab. 2004. Integrating diagnostic expert system with image processing via loosely coupled technique. 2nd International conference on inpormation and systems 1-15.
9. FAOSTAT, 2010. Rice production. Available from: http://faostat.fao.org. Accessed: 20-11-2012.
10. Gomathinayagam, S., M. Rekha, S. Sakthivel Murugan, and R. C. Jagessar. 2009. Biological control of rice disease (blast) by using Trichoerma viride in laboratory conditions. Proceedings of the Caribbean Food Crops Society 45: 79-86.
11. Hemming, J., and T. Rath. 2001. Computer-vision-based weedidentification under field conditions using controlled lighting. Journal of Agricultural Engineering 78 (3): 233-243.
12. Liu, Z., C. Fang, Y. Yi-bin, and R. Xiu-qin. 2005. Identification of rice seed varieties using neural network. Journal of Zhejiang University Science 6 (11): 1095-1100.
13. Moumeni, A., B. Yazdi-samadi, and H. Leung. 2003. An assessment of partial resistance to Pyricularia grisea in rice cultivars. Iranian Journal of Agricultural Science 34 (2): 483-493. (In Farsi).
14. Moya, E. A., L. R. Barrales, and G. E. Apablaza. 2005. Assessment of the disease severity of squash powdery mildew through visual analysis, digital image analysis and validation of these methodologies.
Crop Protection 24 (9): 785-789.
15. Nithya, A., and V. Sundaram. 2011. Identifying the rice diseases using classification andbiosensor techniques. International Journal of Advanced Research in Technology 1 (1): 76-81.
16. Onyango, C. M. 2003. Segmentation of row crop plants from weeds using colour and morphology.
Computers and Electronics in Agriculture 39: 141-155.
17. Otsu, N. 1979. A threshold selection method from gray-level histograms. IEEE transactions on systems, man and cybernetics 9: 62-66.
18. Ou, S. H. 1985. Rice diseases. Common Wealth Mycological Institute. Second Edition. 380p.
19. Sanjay, B., S. B. Patil, and S. K. Bodhe. 2011. Leaf disease severity measurement using image processing. International Journal of Engineering and Technology 3 (5): 297-301.
20. Shouche S. P., R. Rastogi, S. G. Bhagwat, and J. K. Sainis. 2001. Shape analysis ofgrains of Indian wheat varieties. Computers and Electronics in Agriculture 33: 55-76.
21. Skaloudova, B., V. Krivan, and R. Zemek. 2006. Computer-assisted estimation of leaf damage caused by spider mites. Computer and Electronics in Agriculture 53 (2): 81-91.
22. Steddom, K., W. M. Bredehoeft, M. Khan, and M. C. Rush. 2005. Comparison of visual and multispectral radiometric disease evaluations of Cercospora leaf spot of sugar beet. Plant Disease 89: 153-158.
23. Wang, D., M. S. Ramandm, and F. E. Dowell. 2002. Classification of damaged soybean seeds using near- infrared spectroscopy. American Society of Agricultural Engineers 4 (6): 1943-1948.
Exploring the possibility of using digital image processing technique to detect diseases of rice leaf
S. H. Payman1*- A. Bakhshipour Ziaratgahi2- A. Jafari3
Received: 07-02-2014 Accepted: 17-09-2014
Introduction: Rice is a very important staple food crop provides more than half of the world caloric supply.
Rice diseases lead to significant annual crop losses, have negative impacts on quality of the final product and destroy plant variety. Rice Blast is one of the most widespread and most destructive fungal diseases in tropical and subtropical humid areas, which causes significant decrease in the amount of paddy yield and quality of milled rice.
Brown spot disease is another important fungal disease in rice which infects the plant during the rice growing season from the nursery period up to farm growth stage and productivity phase. The later the disease is diagnosed the higher the amount of chemicals is needed for treatment. Due to high costs and harmful environmental impacts of chemical toxins, the accurate early detection and treatment of plant disease is seemed to be necessary.
In general, observation with the naked eye is used for disease detection. However, the results are indeed depend on the intelligence of the person performing the operation. So usually the accurate determination of the severity and progression of the disease can’t be achieved. On the other side, the use of experts for continuous monitoring of large farms might be prohibitively expensive and time consuming. Thus, investigating the new approaches for rapid, automated, inexpensive and accurate plant disease diagnosis is very important.
Machine vision and image processing is a new technique which can capture images from a scene of interest, analyze the images and accurately extract the desired information. Studies show that image processing techniques have been successfully used for plant disease detection.
The aim of this study was to investigate the ability of image processing techniques for diagnosing the rice blast and rice brown spot.
Materials and Methods: The samples of rice leaf infected by brown spot and rice blast diseases were collected from rice fields and the required images were obtained from each sample.The images of infected leaves were then introduced to image processing toolbox of MATLAB software. The RGB images were converted to gray-scale. Using a suitable threshold, the leaf surface was segmented from image background and the first binary image was achieved. Leaf image with zero background pixels was obtained after multiplying the black- and-white image to original color image. The resulting image was transformed to HSV color space and the Hue color component was extracted. The final binary image was created by applying an appropriate threshold on the image that obtained from Hue color component.
As there was a high color similarity between the symptoms of two diseases, it was not possible to use Hue color component to distinguish between them. Therefore the shape processing was applied.
Four dimensionless morphological features such as Roundness, Aspect Ratio, Compactness and Area Ratio were extracted from stain areas and based on these features, disease type diagnosis was performed.
Results and Discussion: Results showed that the proposed algorithm successfully diagnosed the diseases stains on the rice leaves. A detection accuracy of 97.4±1.4 % was achieved.
Regarding the results of t-test, among the extracted shape characteristics, only in the case of Area Ratio, there was no significant difference between two disease symptoms. While in the case of Roundness, Aspect Ratio and Compactness, a highly significant difference (P<0.01) was discovered and revealed between rice blast and rice brown spot stains. The developed algorithm was capable of distinguishing between disease symptoms with an exactness of over 96.6%. This means that of the 60 samples (30 samples rice blast and 30 samples of rice brown spot); only two were placed in the wrong category.
Conclusions: It was concluded from this study that image processing technique can not only accurately
1- Assistant Professor, Department of Agricultural Mechanization Engineering, University of Guilan, Rasht, Iran 2- PhD Scholar, Biosystems Engineering Department, Shiraz University, Shiraz, Iran
3- Aassosiate Professor, Biosystems Engineering Department, Shiraz University, Shiraz, Iran (*- Corresponding Author Email: [email protected])
determine whether the rice is healthy or infected but also can determine the type of plant disease with reliable precision.
Considering the fact that plant diseases spread area by area through the field, early and accurate diagnosis of plant diseases in a part of a farm - which is provided by image processing techniques and machine vision systems – is very useful for timely and effective disease treatment which in turn leads to lower crop losses. Also, by using the site-specific chemical application technologies, the need for chemicals can be minimized, an important factor that can considerably reduce the costs.
Keywords: Brown spot, Machine vision, Rice, Rice blast
