[1] ZHANG J, TANG Z H, AI M X, et al.. Nonlinear modeling of the relationship between reagent dosage and flotation froth surface image by Hammerstein-Wiener model[J]. Minerals Engineering, 2018, 120(5): 19-28.

[2] AI M X, XIE Y F, XIE S W, et al.. Shape-weight. ed bubble size distribution based reagent predictive control for the antimony flotation process[J]. Che. mometrics & Intelligent Laboratory Systems, 2019, 192(8): 103821.

[3] TANG Z H, TANG L Y, ZHANG G Y, et al.. In. telligent setting method of reagent dosage based on time series froth image in zinc flotation process[J]. Processes, 2020, 8(536): 8050536.

[4] LI Z M, GUI W H, ZHU J Y. Fault detection in flotation processes based on deep learning and sup. port vector machine[J]. Journal of Central South University, 2019, 26(9): 2504-2515.

[5] CAO B F, XIE Y F, GUI W H, et al.. Coordinated optimization setting of reagent dosages in roughing-scavenging process of antimony flotation[J]. Journal of Central South University, 2018, 25(1): 95-106.

[7] WANG Y L, SUN B, ZHANG R Q, et al.. Sul. fur flotation performance recognition based on hierar. chical classification of local dynamic and static froth features[J]. IEEE Access, 2018, 6(3): 14019-14029.

[8] NAKHAEI F, IRANNAJAD M, MOHAMMAD. NEJAD S. Evaluation of column flotation froth be. havior by image analysis: effects of operational fac. tors in desulfurization of iron ore concentrate[J]. En. ergy Sources, Part A: Recovery, Utilization, and En. vironmental Effects, 2018, 40(19): 2286-2306.

[9] NAKHAEI F, IRANNAJAD M, MOHAMMAD. NEJAD S. Column flotation performance predic. tion: PCA, ANN and image analysis-based ap. proaches[J]. Physicochemical Problems of Mineral Processing, 2019, 55(5): 1298-1310.

[10] RUBLEE E, RABAUND V, KONOLIGE K, et al.. ORB: An efficientalternative to SIFT or SURF[C]. Int Conf on Computer Vision. Barcelo. na: IEEE, 2011: 2564-2571.

[11] GANASALA P, PRASAD A D. Contrast en. hanced multi sensor image fusion based on guided image filter and NSST[J]. IEEE Sensors Journal, 2020, 20(2): 339-346.

[13] DONG Q, LIU JH, WANG C, et al.. Image mosaic algorithm based on improved BRISK[J]. Journal of Electronics& Information Technology, 2017, 39(2): 444-450.

[15] SONG J L, YANG J H, LIU F J, et al.. High temperature strain measurement method by combin. ing digital image correlation of laser speckle and im. proved RANSAC smoothing algorithm[J]. Optics and Lasers in Engineering, 2018, 111: 8-18.

[18] CHENG Y S, ZHAO D W, WANG Y B, et al.. Multi-label learning with kernel extreme learning machine autoencoder[J]. Knowledge-Based Sys. tems, 2019, 178: 1-10.