Applying Artificial Neural Networks for Face Recognition

<table class="table-group" id="tab7"><tr><td><table class="table"><tr><td class="thead-hr" colspan="7"><hr/></td></tr><tr><td align="left">Method</td><td align="center">SNN1 (<svg height="12.2125" id="M247" style="vertical-align:-3.40982pt" version="1.1" viewbox="0 0 29.725 12.2125" width="29.725" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,7.9)"><path d="M330 461h152v-24q-24 -3 -36 -14t-24 -41l-148 -398q-45 -121 -77 -156q-31 -33 -84 -33q-43 0 -70 22t-27 57q0 29 17 48t45 19q25 0 42.5 -15t17.5 -37l-2 -14l-1 -6q0 -7 5 -12t12 -5q38 0 66 82l18 53l-119 290q-49 121 -67 146q-7 9 -34 14v24h249v-24l-16 -1
q-36 -3 -36 -25q0 -6 20 -58l72 -186l68 188q11 33 11 49q0 18 -11 25t-43 8v24z" id="x1D432"></path></g>
<g transform="matrix(.012,-0,0,-.012,8.562,11.975)"><path d="M14 417v44h57q0 132 40 179q42 51 135 51q64 0 103.5 -28t39.5 -72q0 -28 -17 -46t-45 -18q-25 0 -42.5 17t-17.5 40q0 12 5.5 25t11 22t5.5 10q0 19 -29 19q-27 0 -38.5 -17.5t-11.5 -61.5v-120h86v-44h-86v-310q0 -49 15 -66q14 -15 67 -17v-24h-278v24q34 4 45.5 16.5
t11.5 46.5v330h-57z" id="x1D41F"></path></g><g transform="matrix(.012,-0,0,-.012,12.525,11.975)"><path d="M463 54l10 10l15 -21q-52 -57 -112 -57q-37 0 -55.5 15.5t-26.5 53.5q-76 -69 -159 -69q-52 0 -81 27t-29 79q0 67 67 112q48 32 201 76v68q0 49 -18.5 71t-62.5 22q-28 0 -46.5 -10t-18.5 -27q0 -10 11 -23q19 -22 19 -42q0 -26 -19 -43t-49 -17q-31 0 -48 18t-17 50
q0 59 52 92.5t139 33.5q92 0 144 -35t52 -99v-261q0 -28 21 -28q7 0 11 4zM293 97v148q-122 -35 -122 -121q0 -32 14 -49.5t38 -17.5q42 0 70 40z" id="x1D41A"></path></g><g transform="matrix(.012,-0,0,-.012,18.474,11.975)"><path d="M412 109l18 -18q-41 -56 -86 -80.5t-105 -24.5q-95 0 -155 65q-59 65 -59 171q0 109 68 180t169 71q66 0 110 -31t44 -79q0 -29 -18.5 -46.5t-49.5 -17.5q-26 0 -41 19t-15 54q0 31 -3 44q-4 26 -39 26q-39 0 -61.5 -45t-22.5 -124q0 -102 37 -161t102 -59q57 0 107 56z
" id="x1D41C"></path></g><g transform="matrix(.012,-0,0,-.012,23.757,11.975)"><path d="M403 126l24 -14q-44 -70 -88.5 -98t-109.5 -28q-90 0 -147 67t-57 171q0 112 57 180q58 69 152 69q83 0 128 -50q53 -59 59 -178h-252q6 -81 25 -128q24 -59 94 -59q32 0 58 15.5t57 52.5zM164 282h134v21q0 73 -9 92q-13 26 -24.5 36.5t-30.5 10.5q-37 0 -53.5 -37
t-16.5 -123z" id="x1D41E"></path></g>
</svg>)</td><td align="center">SNN2 (<svg height="14.475" id="M248" style="vertical-align:-5.23482pt" version="1.1" viewbox="0 0 30.387501 14.475" width="30.387501" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,7.9)"><path d="M330 461h152v-24q-24 -3 -36 -14t-24 -41l-148 -398q-45 -121 -77 -156q-31 -33 -84 -33q-43 0 -70 22t-27 57q0 29 17 48t45 19q25 0 42.5 -15t17.5 -37l-2 -14l-1 -6q0 -7 5 -12t12 -5q38 0 66 82l18 53l-119 290q-49 121 -67 146q-7 9 -34 14v24h249v-24l-16 -1
q-36 -3 -36 -25q0 -6 20 -58l72 -186l68 188q11 33 11 49q0 18 -11 25t-43 8v24z" id="x1D432"></path></g>
<g transform="matrix(.012,-0,0,-.012,8.562,11.975)"><path d="M403 126l24 -14q-44 -70 -88.5 -98t-109.5 -28q-90 0 -147 67t-57 171q0 112 57 180q58 69 152 69q83 0 128 -50q53 -59 59 -178h-252q6 -81 25 -128q24 -59 94 -59q32 0 58 15.5t57 52.5zM164 282h134v21q0 73 -9 92q-13 26 -24.5 36.5t-30.5 10.5q-37 0 -53.5 -37
t-16.5 -123z" id="x1D41E"></path></g><g transform="matrix(.012,-0,0,-.012,13.846,11.975)"><path d="M330 461h152v-24q-24 -3 -36 -14t-24 -41l-148 -398q-45 -121 -77 -156q-31 -33 -84 -33q-43 0 -70 22t-27 57q0 29 17 48t45 19q25 0 42.5 -15t17.5 -37l-2 -14l-1 -6q0 -7 5 -12t12 -5q38 0 66 82l18 53l-119 290q-49 121 -67 146q-7 9 -34 14v24h249v-24l-16 -1
q-36 -3 -36 -25q0 -6 20 -58l72 -186l68 188q11 33 11 49q0 18 -11 25t-43 8v24z" id="x1D432"></path></g><g transform="matrix(.012,-0,0,-.012,19.795,11.975)"><path d="M403 126l24 -14q-44 -70 -88.5 -98t-109.5 -28q-90 0 -147 67t-57 171q0 112 57 180q58 69 152 69q83 0 128 -50q53 -59 59 -178h-252q6 -81 25 -128q24 -59 94 -59q32 0 58 15.5t57 52.5zM164 282h134v21q0 73 -9 92q-13 26 -24.5 36.5t-30.5 10.5q-37 0 -53.5 -37
t-16.5 -123z" id="x1D41E"></path></g><g transform="matrix(.012,-0,0,-.012,25.078,11.975)"><path d="M340 471v-145h-25q-20 58 -47 82q-35 32 -75 32q-28 0 -47 -16.5t-19 -41.5q0 -26 22.5 -46.5t73.5 -41.5q75 -31 106.5 -67t31.5 -89q0 -67 -43 -110q-44 -42 -111 -42q-51 0 -108 23q-15 6 -23 6q-11 0 -26 -28h-25v165h28q31 -132 137 -132q34 0 54.5 18t20.5 47
q0 47 -96 87q-75 32 -108.5 68.5t-33.5 86.5q0 63 44 104q45 42 113 42q34 0 78 -15q21 -7 31 -7q17 0 25 20h22z" id="x1D42C"></path></g>
</svg>)</td><td align="center">SNN3 (<svg height="13.525" id="M249" style="vertical-align:-4.4704pt" version="1.1" viewbox="0 0 87.25 13.525" width="87.25" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,7.9)"><path d="M330 461h152v-24q-24 -3 -36 -14t-24 -41l-148 -398q-45 -121 -77 -156q-31 -33 -84 -33q-43 0 -70 22t-27 57q0 29 17 48t45 19q25 0 42.5 -15t17.5 -37l-2 -14l-1 -6q0 -7 5 -12t12 -5q38 0 66 82l18 53l-119 290q-49 121 -67 146q-7 9 -34 14v24h249v-24l-16 -1
q-36 -3 -36 -25q0 -6 20 -58l72 -186l68 188q11 33 11 49q0 18 -11 25t-43 8v24z" id="x1D432"></path></g>
<g transform="matrix(.012,-0,0,-.012,8.562,11.975)"><path d="M14 417v44h57q0 132 40 179q42 51 135 51q64 0 103.5 -28t39.5 -72q0 -28 -17 -46t-45 -18q-25 0 -42.5 17t-17.5 40q0 12 5.5 25t11 22t5.5 10q0 19 -29 19q-27 0 -38.5 -17.5t-11.5 -61.5v-120h86v-44h-86v-310q0 -49 15 -66q14 -15 67 -17v-24h-278v24q34 4 45.5 16.5
t11.5 46.5v330h-57z" id="x1D41F"></path></g><g transform="matrix(.012,-0,0,-.012,12.525,11.975)"><path d="M463 54l10 10l15 -21q-52 -57 -112 -57q-37 0 -55.5 15.5t-26.5 53.5q-76 -69 -159 -69q-52 0 -81 27t-29 79q0 67 67 112q48 32 201 76v68q0 49 -18.5 71t-62.5 22q-28 0 -46.5 -10t-18.5 -27q0 -10 11 -23q19 -22 19 -42q0 -26 -19 -43t-49 -17q-31 0 -48 18t-17 50
q0 59 52 92.5t139 33.5q92 0 144 -35t52 -99v-261q0 -28 21 -28q7 0 11 4zM293 97v148q-122 -35 -122 -121q0 -32 14 -49.5t38 -17.5q42 0 70 40z" id="x1D41A"></path></g><g transform="matrix(.012,-0,0,-.012,18.474,11.975)"><path d="M412 109l18 -18q-41 -56 -86 -80.5t-105 -24.5q-95 0 -155 65q-59 65 -59 171q0 109 68 180t169 71q66 0 110 -31t44 -79q0 -29 -18.5 -46.5t-49.5 -17.5q-26 0 -41 19t-15 54q0 31 -3 44q-4 26 -39 26q-39 0 -61.5 -45t-22.5 -124q0 -102 37 -161t102 -59q57 0 107 56z
" id="x1D41C"></path></g><g transform="matrix(.012,-0,0,-.012,23.757,11.975)"><path d="M403 126l24 -14q-44 -70 -88.5 -98t-109.5 -28q-90 0 -147 67t-57 171q0 112 57 180q58 69 152 69q83 0 128 -50q53 -59 59 -178h-252q6 -81 25 -128q24 -59 94 -59q32 0 58 15.5t57 52.5zM164 282h134v21q0 73 -9 92q-13 26 -24.5 36.5t-30.5 10.5q-37 0 -53.5 -37
t-16.5 -123z" id="x1D41E"></path></g>
<g transform="matrix(.012,-0,0,-.012,29.037,11.975)"><path d="M500 -125h-500v50h500v-50z" id="x5F"></path></g>
<g transform="matrix(.012,-0,0,-.012,34.988,11.975)"><path d="M539 24v-24h-234v24q25 3 35.5 16.5t10.5 43.5v237q0 85 -51 85q-36 0 -70 -34q-17 -17 -17 -24v-264q0 -29 10.5 -42.5t37.5 -17.5v-24h-240v24q33 7 43 19t10 44v289q0 32 -10 44t-43 17v24h191v-75h1q49 87 142 87q62 0 98.5 -38.5t36.5 -103.5v-247q0 -34 10 -46
t39 -14z" id="x1D427"></path></g><g transform="matrix(.012,-0,0,-.012,41.603,11.975)"><path d="M476 229q0 -104 -65 -174q-65 -69 -161 -69q-95 0 -160 68q-65 70 -65 174q0 110 64 177q65 68 165 68q95 0 158 -69q64 -68 64 -175zM329 218q0 127 -17 176q-16 48 -61 48q-47 0 -63 -48q-16 -45 -16 -176q0 -109 18 -155t61 -46t60.5 45t17.5 156z" id="x1D428"></path></g>
<g transform="matrix(.012,-0,0,-.012,47.55,11.975)"><path d="M500 -125h-500v50h500v-50z" id="x5F"></path></g>
<g transform="matrix(.012,-0,0,-.012,53.5,11.975)"><path d="M814 24v-24h-237v24q28 2 38 14.5t10 44.5v228q0 95 -53 95q-30 0 -58 -25q-9 -7 -18 -18t-9 -15v-265q0 -30 10 -43t36 -16v-24h-232v24q27 2 37 15t10 44v240q0 45 -12.5 64t-41.5 19q-18 0 -52 -23q-32 -23 -32 -39v-261q0 -30 9.5 -42.5t35.5 -16.5v-24h-239v24
q33 6 44 18.5t11 43.5v287q0 35 -11 47t-45 17v24h192v-75h3q30 46 63 66.5t81 20.5q47 0 76 -19.5t52 -67.5q39 48 71.5 67.5t75.5 19.5q62 0 98.5 -38t36.5 -104v-248q0 -33 10.5 -45.5t39.5 -13.5z" id="x1D426"></path></g><g transform="matrix(.012,-0,0,-.012,63.412,11.975)"><path d="M476 229q0 -104 -65 -174q-65 -69 -161 -69q-95 0 -160 68q-65 70 -65 174q0 110 64 177q65 68 165 68q95 0 158 -69q64 -68 64 -175zM329 218q0 127 -17 176q-16 48 -61 48q-47 0 -63 -48q-16 -45 -16 -176q0 -109 18 -155t61 -46t60.5 45t17.5 156z" id="x1D428"></path></g><g transform="matrix(.012,-0,0,-.012,69.361,11.975)"><path d="M538 43v-23l-63 -7q-80 -9 -132 -26v65q-39 -37 -71.5 -51.5t-73.5 -14.5q-63 0 -98 38t-35 107v241q0 35 -9 47t-40 18v24h188v-334q0 -76 56 -76q38 0 82 47v276q0 34 -12.5 47t-48.5 16v24h200v-356q0 -34 12.5 -47.5t44.5 -14.5z" id="x1D42E"></path></g><g transform="matrix(.012,-0,0,-.012,75.977,11.975)"><path d="M307 112l25 -11q-31 -62 -64.5 -87.5t-83.5 -25.5q-52 0 -82 28.5t-30 78.5v322h-53v27q47 31 82 71q32 38 85 115h25v-169h95v-44h-95v-298q0 -60 39 -60q28 0 57 53z" id="x1D42D"></path></g><g transform="matrix(.012,-0,0,-.012,79.939,11.975)"><path d="M534 24v-24h-234v24q25 3 35.5 16.5t10.5 44.5v224q0 54 -11 75.5t-40 21.5q-36 0 -70 -34q-17 -17 -17 -24v-263q0 -31 10 -44t38 -17v-24h-240v24q37 8 44 16q9 9 9 49v502q0 35 -9 44q-8 9 -45 17v24h193v-280q65 77 147 77q59 0 94.5 -37.5t35.5 -98.5v-250
q0 -34 11.5 -48.5t37.5 -14.5z" id="x1D421"></path></g>
</svg>)</td><td align="center">GICA</td><td align="center">Average</td><td align="center">MANN</td></tr><tr><td align="center" colspan="7"><hr/></td></tr><tr><td align="left">Precision</td><td align="center">93.25</td><td align="center">91.11</td><td align="center">94.75</td><td align="center">96.57</td><td align="center">96.84</td><td align="center">98.91</td></tr><tr class="table-tr"><td colspan="7"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Percentage accuracy values on the CalTech database (%).

Advances in Artificial Neural Systems

tab7

Table 7

Table 7: Applying Artificial Neural Networks for Face Recognition 