Random Binary Local Patch Clustering Transforms Based Image Matching for Nonlinear Intensity Changes

<div>Examples of the multiple support region-based RBPPC descriptor: (a1), (b1) RGB/LWIR input image patch pair; (a2), (b2) an input image patch pair featuring different exposures; (a3), (b3) an input image patch pair featuring illumination changes; (c1), (c2), (c3) <svg height="11.6836pt" id="M79" style="vertical-align:-3.29562pt" version="1.1" viewbox="-0.0498162 -8.38798 15.6586 11.6836" width="15.6586pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M861 0V28C774 35 771 41 768 147L759 509C756 612 762 614 851 622V650H681L449 149L221 650H57V622C148 613 153 609 144 479L130 271C123 166 117 123 111 88C104 46 85 34 26 28V0H259V28C192 35 169 42 167 90C166 130 166 173 170 256L185 541H187L411 7H431L675 555H679L683 147C683 41 680 35 598 28V0H861Z" id="g121-75"></path></g><g transform="matrix(.0091,0,0,-0.0091,11.583,3.132)"><path d="M327 325C324 350 312 408 304 433C283 442 256 451 213 451C120 451 59 391 59 320C59 243 125 210 188 181C237 158 266 136 266 93C266 52 231 24 195 24C134 24 93 81 74 148L42 143C42 106 51 37 59 23C78 8 125 -12 177 -12C257 -12 345 35 345 127C345 198 292 234 216 264C171 283 131 305 131 348C131 387 156 416 195 416C243 416 277 378 297 317L327 325Z" id="g58-113"></path></g></svg> from the respective source images; (d1), (d2), (d3) <svg height="11.6151pt" id="M80" style="vertical-align:-3.227119pt" version="1.1" viewbox="-0.0498162 -8.38798 18.0609 11.6151" width="18.0609pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M861 0V28C774 35 771 41 768 147L759 509C756 612 762 614 851 622V650H681L449 149L221 650H57V622C148 613 153 609 144 479L130 271C123 166 117 123 111 88C104 46 85 34 26 28V0H259V28C192 35 169 42 167 90C166 130 166 173 170 256L185 541H187L411 7H431L675 555H679L683 147C683 41 680 35 598 28V0H861Z" id="g121-75"></path></g><g transform="matrix(.0091,0,0,-0.0091,11.583,3.132)"><path d="M639 21C616 28 593 39 566 68C542 92 523 117 486 170C457 215 415 282 397 314C472 346 524 398 524 485C524 545 497 590 456 617C417 641 369 650 296 650H43V617C122 612 130 608 130 523V129C130 45 122 38 38 33V0H306V33C225 38 216 45 216 129V282H249C302 282 319 270 336 243C365 195 401 132 436 84C483 18 525 -5 597 -8C610 -9 622 -9 635 -9L639 21ZM216 319V559C216 586 219 596 227 603S250 613 281 613C356 613 429 576 429 469C429 416 413 379 374 348C349 327 316 319 265 319H216Z" id="g58-80"></path></g></svg> from the respective reference images; (e1), (e2), (e3) multiple support region-based RBPPCs of the source images; (f1), (f2), (f3) multiple support region-based RBPPCs of the reference images.</div>

Mathematical Problems in Engineering

fig12

Figure 12

Figure 12: Random Binary Local Patch Clustering Transforms Based Image Matching for Nonlinear Intensity Changes 